• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.85-92
• /
• 2022

In this paper, we propose a technique that can express low-resolution hair and fur simulations in high-resolution without noise using ConvNet and geometric images of strands in the form of lines. Pairs between low-resolution and high-resolution data can be obtained through physics-based simulation, and a low-resolution-high-resolution data pair is established using the obtained data. The data used for training is used by converting the position of the hair strands into a geometric image. The hair and fur network proposed in this paper is used for an image synthesizer that upscales a low-resolution image to a high-resolution image. If the high-resolution geometry image obtained as a result of the test is converted back to high-resolution hair, it is possible to express the elastic movement of hair, which is difficult to express with a single mapping function. As for the performance of the synthesis result, it showed faster performance than the traditional physics-based simulation, and it can be easily executed without knowing complex numerical analysis.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.687-701
• /
• 2022

Inevitable response loss under complex operational conditions significantly affects the integrity and quality of measured data, leading the structural health monitoring (SHM) ineffective. To remedy the impact of data loss, a common way is to transfer the recorded response of available measure point to where the data loss occurred by establishing the response mapping from measured data. However, the current research has yet addressed the structural condition changes afterward and response mapping learning from a small sample. So, this paper proposes a novel data driven structural response reconstruction method based on a sophisticated designed generating adversarial network (UAGAN). Advanced deep learning techniques including U-shaped dense blocks, self-attention and a customized loss function are specialized and embedded in UAGAN to improve the universal and representative features extraction and generalized responses mapping establishment. In numerical validation, UAGAN efficiently and accurately captures the distinguished features of structural response from only 40 training samples of the intact structure. Besides, the established response mapping is universal, which effectively reconstructs responses of the structure suffered up to 10% random stiffness reduction or structural damage. In the experimental validation, UAGAN is trained with ambient response and applied to reconstruct response measured under earthquake. The reconstruction losses of response in the time and frequency domains reached 16% and 17%, that is better than the previous research, demonstrating the leading performance of the sophisticated designed network. In addition, the identified modal parameters from reconstructed and the corresponding true responses are highly consistent indicates that the proposed UAGAN is very potential to be applied to practical civil engineering.

• Journal of the Korean Society of Physical Medicine
• /
• v.17 no.4
• /
• pp.45-52
• /
• 2022

PURPOSE: This study examined the center of pressure (COP) and ground reaction force (GRF) characteristics during each task-oriented sit-to-stand in stroke patients. METHODS: Twenty stroke subjects were included in this study. The task consisted of sit-to-stand (SS), sit-to-stand for reaching (SR), and sit-to-stand for walking (SW). The response time, COP, and GRF were measured during each task. The COP and GRF data were obtained using a two-force plate. The force plates were placed on a chair (below the buttock) and floor (below the feet). RESULTS: Significant differences were observed between SS (1.48 ± .48 s) and SR (2.09 ± 0.82 s) and between SS and SW (2.27 ± .72 s) in the preparatory phase time during each sit-to-stand exercise (p = .002) and showed significant differences between SS (13.90 ± 6.44 cm) and SW (34.62 ± 39.38 cm) and between SR (16.14 ± 8.04 cm) and SW in the mediolateral COP range during each sit-to-stand exercise (p = .013). CONCLUSION: These findings suggest that more complex task-oriented sit-to-stand exercise requires a high-level motor programming process than a simple sit-to-stand task. Therefore, a variety of tasks-oriented sit-to-stand exercises will be useful training to achieve better ADL ability for stroke patients.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.117-127
• /
• 2022

Data anomalies seriously threaten the reliability of the bridge structural health monitoring system and may trigger system misjudgment. To overcome the above problem, an efficient and accurate data anomaly detection method is desiderated. Traditional anomaly detection methods extract various abnormal features as the key indicators to identify data anomalies. Then set thresholds artificially for various features to identify specific anomalies, which is the artificial experience method. However, limited by the poor generalization ability among sensors, this method often leads to high labor costs. Another approach to anomaly detection is a data-driven approach based on machine learning methods. Among these, the bidirectional long-short memory neural network (BiLSTM), as an effective classification method, excels at finding complex relationships in multivariate time series data. However, training unprocessed original signals often leads to low computation efficiency and poor convergence, for lacking appropriate feature selection. Therefore, this article combines the advantages of the two methods by proposing a deep learning method with manual experience statistical features fed into it. Experimental comparative studies illustrate that the BiLSTM model with appropriate feature input has an accuracy rate of over 87-94%. Meanwhile, this paper provides basic principles of data cleaning and discusses the typical features of various anomalies. Furthermore, the optimization strategies of the feature space selection based on artificial experience are also highlighted.

• Journal of The Korean Society of Integrative Medicine
• /
• v.10 no.1
• /
• pp.81-89
• /
• 2022

Purpose : Kegel exercises reported that it is effective in managing stress-related or complex urinary incontinence through contraction and relaxation of the pelvic floor muscles. In many previous studies, it was confirmed that Kegel exercise is involved in respiration as well as urinary system diseases. However, there is a lack of research on the effect of pelvic setting when performing Kegel exercises. Therefore, this study was conducted to investigate the effect on maximum voluntary ventilation (MVV) and abdominal muscle thickness through Kegel exercise after lumbar-pelvic motor control using pressure biofeedback unit (PBU). Methods : The subjects of this study were 10 healthy female students in their 20s. Subjects measured MVV with a spirometer. In hooklying, external oblique, internal oblique, and transverse abdominis of the dominant hand were measured using ultrasound. The measured value was an average of three times. After one week of intervention, measurements were made in the same manner. Before Kegel exercise, pelvic setting training was performed using PBU. In hooklying, PBU was placed in the waist and set to 40 mmHg, and it was adjusted to 60 mmHg through pelvic muscle contraction. For Kegel exercise, the pelvis was first set using PBU, and then the pelvic floor muscles were contracted for 8 seconds and relaxed for 8 seconds, 10 times, 1 set, and 3 sets. Results : In MVV, a significant difference was confirmed after exercise than before exercise (p<.05). There was also a significant difference in abdominal muscle thickness before and after exercise (p<.05). Conclusion : Based on the results of this study, Kegel exercise using PBU had an effect on MVV and abdominal muscle thickness. However, since this study was conducted without a control group as a preliminary study, additional research should be conducted to supplement this.

• Ocean and Polar Research
• /
• v.45 no.2
• /
• pp.43-55
• /
• 2023

This study was conducted to understand the seasonal patterns and variation of the copepod community in the Anma Islands of Yeonggwang, Yellow Sea, with a focus on seasonal surveys to assess the factors affecting their occurrence. Throughout the survey period, Acartia hongi, Paracalanus parvus s. l., and Ditrichocorycaeus affinis were dominant species, while Acartia ohtsukai, Acartia pacifica, Bestiolina coreana, Centropages abdominalis, Labidocera rotunda, Paracalanus sp., Tortanus derjugini, Tortanus forcipatus occurred differently by season and station. As a results of cluster analysis, the copepod communities were distinguished into three distinct groups: spring-winter, summer, and autumn. The results of this study showed that the occurrence patterns of copepod species can vary depending on environmental conditions (topographic, distance from the inshore, etc.), and their spatial occurrence patterns between seasons were controlled by water temperature and prey conditions. One of the physical mechanisms that can affect the distribution of zooplankton in the Yellow Sea is the behavior of the Yellow Sea Bottom Cold Water (YSBCW), which shows remarkable seasonal fluctuations. More detailed further studies are needed for clear grounds for mainly why to many Calanus sinicus in the central region of the Yellow Sea are seasonally moving to the inshore, what strategies to seasonally maintain the population, and support the possibilities of complex factors.

• Journal of IKEEE
• /
• v.26 no.1
• /
• pp.62-66
• /
• 2022

Recently, there have been many research efforts based on data-based deep learning technologies to deal with the interference problem between heterogeneous wireless communication devices in unlicensed frequency bands. However, existing approaches are commonly based on the use of complex neural network models, which require high computational power, limiting their efficiency in resource-constrained network interfaces and Internet of Things (IoT) devices. In this study, we address the problem of classifying heterogeneous wireless technologies including Wi-Fi and ZigBee in unlicensed spectrum bands. We focus on a data-driven approach that employs a supervised-learning method that uses received signal strength indicator (RSSI) data to train Deep Convolutional Neural Networks (CNNs). We propose a simple measurement methodology for collecting RSSI training data which preserves temporal and spectral properties of the target signal. Real experimental results using an open-source 2.4 GHz wireless development platform Ubertooth show that the proposed sampling method maintains the same accuracy with only a 10% level of sampling data for the same neural network architecture.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2019.11a
• /
• pp.271-271
• /
• 2019

Estimating ship motion is difficult because it take place in complex environments.. Estimating ship motion is an important factor in ensuring the safety of ship, so accurate estimates are needed. Existing motion-related studies compare the apparent motion of the model acquired and the reference model by experimenting with the ship motion on a particular alignment, making it difficult to intuitively estimate the hull motion. This study introduces the concept of estimating the characteristics of ship motion as a transfer function through pole-zero interpretation and frequency response analysis by applying the method of transfer function of Linear-Time Invariant system. Ship motion analysis model using Linear-Time Invariant system is consist with 1) wave as input signal 2) ship motion as output signal 3) hull defined as black box. This model can be defined by numericalizing the ship motion as a transfer function and is expected to facilitate the characterization of the ship motion through pole-zero analysis and frequency response analysis.

• Journal of Information Science Theory and Practice
• /
• v.10 no.spc
• /
• pp.143-153
• /
• 2022

With the development of networks and the increase in the number of network devices, the number of cyber attacks targeting them is also increasing. Since these cyber-attacks aim to steal important information and destroy systems, it is necessary to minimize social and economic damage through early detection and rapid response. Many studies using machine learning (ML) and artificial intelligence (AI) have been conducted, among which payload learning is one of the most intuitive and effective methods to detect malicious behavior. In this study, we propose a preprocessing method to maximize the performance of the model when learning the payload in term units. The proposed method constructs a high-quality learning data set by eliminating unnecessary noise (stopwords) and preserving important features in consideration of the machine language and natural language characteristics of the packet payload. Our method consists of three steps: Preserving significant special characters, Generating a stopword list, and Class label refinement. By processing packets of various and complex structures based on these three processes, it is possible to make high-quality training data that can be helpful to build high-performance ML/AI models for security monitoring. We prove the effectiveness of the proposed method by comparing the performance of the AI model to which the proposed method is applied and not. Forthermore, by evaluating the performance of the AI model applied proposed method in the real-world Security Operating Center (SOC) environment with live network traffic, we demonstrate the applicability of the our method to the real environment.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.207-215
• /
• 2023

The ship system is complex and advanced, and the operation relationship between each element is very high. So it is necessary to approach it in terms of an overall and integrated system in addition to the traditional sequential approach of finding and removing the direct cause of the accident when analyzing the accident. In this study, it is analyzed the recent fire accidents on ships occurred the Korean terrestrial water using a STAMP methodology that is different from conventional accident analysis techniques. This analysis reviews a range of factors, including safety requirements to prevent fires in ships, inappropriate decisions and actions, situations, equipment defects, and recommendations derived from accident analysis results. Through a comprehensive approach to accident prevention using STAMP, alternative evaluations are presented at the component level within the entire system of ships, and they are systematically used for accident prevention and risk evaluation as well as simple accident analysis.