• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.145-151
• /
• 2023

3D-CNN is one of the deep learning techniques for learning time series data. Such three-dimensional learning can generate many parameters, so that high-performance machine learning is required or can have a large impact on the learning rate. When learning dynamic hand-gestures in spatiotemporal domain, it is necessary for the improvement of the efficiency of dynamic hand-gesture learning with 3D-CNN to find the optimal conditions of input video data by analyzing the learning accuracy according to the spatiotemporal change of input video data without structural change of the 3D-CNN model. First, the time ratio between dynamic hand-gesture actions is adjusted by setting the learning interval of image frames in the dynamic hand-gesture video data. Second, through 2D cross-correlation analysis between classes, similarity between image frames of input video data is measured and normalized to obtain an average value between frames and analyze learning accuracy. Based on this analysis, this work proposed two methods to effectively select input video data for 3D-CNN deep learning of dynamic hand-gestures. Experimental results showed that the learning interval of image data frames and the similarity of image frames between classes can affect the accuracy of the learning model.

• Animal Bioscience
• /
• v.36 no.10
• /
• pp.1517-1529
• /
• 2023

Objective: The objective of this study was to investigate the phylogenetic and expression analysis of the angiopoietin-like (ANGPTL) gene family and their role in lipid metabolism in pigs. Methods: In this study, the amino acid sequence analysis, phylogenetic analysis, and chromosome adjacent gene analysis were performed to identify the ANGPTL gene family in pigs. According to the body weight data from 60 Jinhua pigs, different tissues of 6 pigs with average body weight were used to determine the expression profile of ANGPTL1-8. The ileum, subcutaneous fat, and liver of 8 pigs with distinct fatness were selected to analyze the gene expression of ANGPTL3, ANGPTL4, and ANGPTL8. Results: The sequence length of ANGPTLs in pigs was between 1,186 and 1,991 bp, and the pig ANGPTL family members shared common features with human homologous genes, including the high similarity of the amino acid sequence and chromosome flanking genes. Amino acid sequence analysis showed that ANGPTL1-7 had a highly conserved domain except for ANGPTL8. Phylogenetic analysis showed that each ANGPTL homologous gene shared a common origin. Quantitative reverse-transcription polymerase chain reaction analysis showed that ANGPTL family members had different expression patterns in different tissues. ANGPTL3 and ANGPTL8 were mainly expressed in the liver, while ANGPTL4 was expressed in many other tissues, such as the intestine and subcutaneous fat. The expression levels of ANGPTL3 in the liver and ANGPTL4 in the liver, intestine and subcutaneous fat of Jinhua pigs with low propensity for adipogenesis were significantly higher than those of high propensity for adipogenesis. Conclusion: These results increase our knowledge about the biological role of the ANGPTL family in this important economic species, it will also help to better understand the role of ANGPTL3, ANGPTL4, and ANGPTL8 in lipid metabolism of pigs, and provide innovative ideas for developing strategies to improve meat quality of pigs.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.329-344
• /
• 2023

In this study, we comprehensively analyze the generalization performance of various deep learning-based active sonar target classifiers when applied to small and imbalanced active sonar datasets. To generate the active sonar datasets, we use data from two different oceanic experiments conducted at different times and ocean. Each sample in the active sonar datasets is a time-frequency domain image, which is extracted from audio signal of contact after the detection process. For the comprehensive analysis, we utilize 22 Convolutional Neural Networks (CNN) models. Two datasets are used as train/validation datasets and test datasets, alternatively. To calculate the variance in the output of the target classifiers, the train/validation/test datasets are repeated 10 times. Hyperparameters for training are optimized using Bayesian optimization. The results demonstrate that shallow CNN models show superior robustness and generalization performance compared to most of deep CNN models. The results from this paper can serve as a valuable reference for future research directions in deep learning-based active sonar target classification.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.3A
• /
• pp.341-347
• /
• 2008

Among coating systems used for steel bridge coatings on highway such as red lead-pigmented alkyd, chlorinated rubber, waterborne inorganic zinc, inorganic zinc/epoxy/urethane and inorganic zinc/epoxy/fluororesin, evaluation of deterioration degree and prediction of lifetime through regression analysis were carried out for coating systems widely used and grossly degraded. For evaluation of deterioration degree, 75 bridges on highway were selected, and evaluations were carried out according to point offering method regulated by Guideline of maintenance coating for steel bridges used in Korea Expressway Corporation. Lifetime prediction results showed 13.0~13.3 years for the whole nation, 11.8 years for urban and industrial region in the metropolitan area, 13.2 years for rural region except the metropolitan area, 13.5~13.7 years for chlorinated rubber coating systems, and 12.86 years for red lead-pigmented alkyd systems. For prediction of the rest life of coating, we tried to execute parallel translations of standard deterioration curve to current life and deterioration degree for both x and y axes, and it was thought that parallel translation for x axis corresponded to deterioration aspects in actual environment. Maximum and minimum equations were derived from standard deterioration equation by adding and subtracting error values deduced in regression analysis to/from each coefficient in order to establish maintenance coating criteria for overall steel bridges on highway. Whole domain was divided into 8 parts in order to predict the rest life of coating and optimum time of maintenance coating, and maintenance coating criteria for each 8 domains were presented.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.2C
• /
• pp.109-120
• /
• 2006

SPT-Uphole test is a seismic field test using receivers on ground surface and a SPT (Standard penetration test) source in depth. Even though this method is simple and economic, it makes hesitate to apply in real field that it is difficult to obtain reliable travel time information of shear wave because of the characteristics of SPT impact source. To overcome this shortcoming, in this paper, modified SPT-Uphole method using two component surface geophones was suggested. Numerical analysis was performed using finite element method for understanding the characteristics of surface motion induced by in-depth vertical source, and comparison study of the various methods which determine the travel time information in SPT-Uphole method was performed. In result, it is thought that the most reasonable method is using the first local maximum point of the root mean square value signals of vertical and horizontal component in time domain. Finally, modified SPT-Uphole method using two component surface geophones was performed at the site, and the applicability in field was verified by comparing wave velocity profiles determined by the SPT-Uphole method with the profiles determined by SASW method and SPT-N values.

• Clean Technology
• /
• v.29 no.4
• /
• pp.305-312
• /
• 2023

Due to the strengthening of environmental requirements, aging denitrification facilities need to improve their performance. The present study aims to suggest the possibility of improving performance using computational analysis techniques. This involved modifying both the geometric design and the operating conditions, including the flow path shape of the equipment such as the inlet guide vane and the curved diffusing part, and the flow control of the ammonia injection nozzle. The conditions presented in this study were compared with existing operating conditions in terms of the flow uniformity, the NH₃/NO molar ratio of the mixed gas flowing into the catalyst layer, and the total pressure drop of the facility. The flow field applied in the computational analysis ranged from the outlet of the economizer in the combustion furnace to the inlet of the air preheater, the full domain of the denitrification facility. The performances were derived by solving the flow fields using ANSYS-Fluent and the injection amount of ammonia was adjusted for each nozzle using Design Xplorer. Compared to the denitrification performances of the equipment currently in operation, the conditions proposed in this study showed an improvement in the flow uniformity and NH₃/NO composition ratio by 45.1% and 8.7%, respectively, but the total pressure drop increased by 1.24%.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1031-1040
• /
• 2023

Propagation characteristics in line-of-sight(LOS) paths in 3, 6, 10, and 17 GHz frequency bands were measured and analyzed in two different indoor corridors: second floors of Buildings D2 and E2. The measurement was designed to measure when the receiving antenna moved at 0.5 m intervals from 3 m to 30 m, while the transmission antenna was fixed. The analysis of the two indoor corridors was compared by applying basic transmission loss, root mean square (RMS) delay spread, and K-factor. For basic transmission loss, the loss coefficient of the floating intercept path loss model was higher in the indoor corridor of Building E2 than in that of Building D2. Similarly, the RMS delay spread in the time domain was greater in the indoor corridor of Building E2. However, the indoor corridor of Building D2 exhibited higher K-factor in the 3, 6, and 17 GHz bands with lower wave propagation in the 10 GHz band. Despite the 2 indoor corridors being identical, the propagation characteristics varied due to different internal structures and materials. The results provide measurement data for ITU-R Recommendations regarding various indoor environments.

• Journal of Navigation and Port Research
• /
• v.47 no.6
• /
• pp.315-323
• /
• 2023

Marine accidents due to loss of stability of small ships have continued to increase over the past decade. In particular, since sudden winds have been pointed out as main causes of most small ship accidents, safety measures have been established to prevent them. In this regard, to prevent accidents caused by sudden winds, a systematic analysis technique is required. The aim of the present study was to develop a probabilistic approach to estimate extreme value and evaluate effects of wind on motion characteristics of ships. The present study included studies of motion analysis, extraction of extreme values, and motion characteristics. A series analysis was conducted for three conditions: wave only, wave with uniform wind speed, and wave with the NPD wind model. Hysteresis filtering and Peak-Valley filtering techniques were applied to time-domain motion analysis results for extreme value extraction. Using extracted extreme values, the goodness of fit test was performed on four distribution functions to select the optimal distribution-function that best expressed extreme values. Motion characteristics of a fishing boat were evaluated for three periodic motion conditions (Heave, Roll, and Pitch) and results were compared. Numerical analysis was performed using a commercial solver, ANSYS-AQWA.

• Journal of the Korea Society for Simulation
• /
• v.33 no.2
• /
• pp.37-44
• /
• 2024

The Korean Helicopter Development Program has successfully introduced the Surion helicopter, a versatile multi-domain operational aircraft that replaces the aging UH-1 and 500MD helicopters. Specifically designed for maneuverability, the Surion plays a crucial role in low-altitude tactical maneuvers for personnel transportation and specific missions, emphasizing the helicopter's survivability. Despite the significance of its low-altitude tactical maneuver capability, there is a notable gap in research focusing on multi-mission tactical maneuvers that consider the risk factors associated with deploying the Surion in the presence of enemy air defenses. This study addresses this gap by exploring a method to enhance the Surion's low-altitude maneuvering paths, incorporating information about enemy air defenses. Leveraging the Proximal Policy Optimization (PPO) algorithm, a reinforcement learning-based approach, the research aims to optimize the helicopter's path planning. Visualized experiments were conducted using a Surion model implemented in the Unity environment and ML-Agents library. The proposed method resulted in a rapid and stable policy convergence for generating optimal maneuvering paths for the Surion. The experiments, based on two key criteria, "operation time" and "minimum damage," revealed distinct optimal paths. This divergence suggests the potential for effective tactical maneuvers in low-altitude situations, considering the risk factors associated with enemy air defenses. Importantly, the Surion's capability for remote control in all directions enhances its adaptability in complex operational environments.

• Informatization Policy
• /
• v.31 no.2
• /
• pp.3-38
• /
• 2024

Hallucination is a significant barrier to the utilization of large-scale language models or multimodal models. In this study, we collected 654 computer science papers with "hallucination" in the abstract from arXiv from December 2022 to January 2024 following the advent of Chat GPT and conducted frequency analysis, knowledge network analysis, and literature review to explore the latest trends in hallucination research. The results showed that research in the fields of "Computation and Language," "Artificial Intelligence," "Computer Vision and Pattern Recognition," and "Machine Learning" were active. We then analyzed the research trends in the four major fields by focusing on the main authors and dividing them into data, hallucination detection, and hallucination mitigation. The main research trends included hallucination mitigation through supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF), inference enhancement via "chain of thought" (CoT), and growing interest in hallucination mitigation within the domain of multimodal AI. This study provides insights into the latest developments in hallucination research through a technology-oriented literature review. This study is expected to help subsequent research in both engineering and humanities and social sciences fields by understanding the latest trends in hallucination research.