• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.59-66
• /
• 2021

Humans mainly recognize surrounding objects using visual and auditory information among the five senses (sight, hearing, smell, touch, taste). Major research related to the latest object recognition mainly focuses on analysis using image sensor information. In this paper, after emitting various chirp audio signals into the observation space, collecting echoes through a 2-channel receiving sensor, converting them into spectral images, an object recognition experiment in 3D space was conducted using an image learning algorithm based on deep learning. Through this experiment, the experiment was conducted in a situation where there is noise and echo generated in a general indoor environment, not in the ideal condition of an anechoic room, and the object recognition through echo was able to estimate the position of the object with 83% accuracy. In addition, it was possible to obtain visual information through sound through learning of 3D sound by mapping the inference result to the observation space and the 3D sound spatial signal and outputting it as sound. This means that the use of various echo information along with image information is required for object recognition research, and it is thought that this technology can be used for augmented reality through 3D sound.

• Journal of Korea Water Resources Association
• /
• v.54 no.8
• /
• pp.567-576
• /
• 2021

Climate change threatens the security of domestic water resources in South Korea. To overcome the potential water shortage, various approaches are being studied by alterning the operation of dams or by integrated operation of multiple dams and reservoirs. However, most of the related researches were developed and applied for multi-purpose dams, and few studies were conducted for the hydropower dams. The main purpose of the hydropower dam is to generate electric energy; however, the potential water shortage due to prolonged droughts brings the idea to supply water from the hydropower dam in the basin. To that end, it is required to estimate the water supply ability of the hydropower dams. In this study, we proposed a methodology to classify the hydropower dam into a "storage-type" and "run-of-river type" dam. The proposed approach was demonstrated using the hydropower dams located in North-han River basin. The results of this study are expected to contribute for further analysis of the hydropower dams, such as evaluation of water supply capacity and drought mitigation purpose operation of the hydropower dams.

• Journal of Korea Water Resources Association
• /
• v.55 no.1
• /
• pp.71-84
• /
• 2022

The objective of this study is to develop a two-dimensional (2D) flood model that can perform accurate flood analysis with simple input data. The 2D flood inundation models currently used to create flood forecast maps require complex input data and grid generation tools. This sometimes requires a lot of time and effort for flood modeling, and there may be difficulties in constructing input data depending on the situation. In order to compensate for these shortcomings, in this study, a grid-based model that can derive accurate and rapid flood analysis by reflecting correct topography as simple input data was developed. The calculation efficiency was improved by extending the existing 2×2 sub-grid model to a 5×5. In order to examine the accuracy and applicability of the model, it was applied to the Gamcheon Basin where both urban and river flooding occurred due to Typhoon Rusa. For efficient flood analysis according to user's selection, flood wave propagation patterns, accuracy and execution time according to grid size and number of sub-grids were investigated. The developed model is expected to be highly useful for flood disaster mapping as it can present the results of flooding analysis for various situations, from the flood inundation map showing accurate flooding to the flood risk map showing only approximate flooding.

• Explosives and Blasting
• /
• v.39 no.4
• /
• pp.22-33
• /
• 2021

Recently, the frequent occurrence of ground subsidence in urban areas has caused increasing anxiety in residents and incurred significant social costs. Among the causes of ground subsidence, the rupture of old water and sewer pipes not only halts the operation of the buried pipes, but also leads to ground and water pollution problems. However, because most pipes are buried after construction and cannot be seen with the naked eye, the importance of maintenance has underestimated compared to other structures. In recent years, integrated physical exploration has been applied to the maintenance of underground pipes and structures. Currently, to investigate the internal conditions and vulnerable portions of the ground, consolidated physical surveys are executed. Consolidated physical surveys are analysis techniques that obtain various material data and add existing data using multiple physical surveys. Generally, in geotechnical engineering, consolidated physical surveys including electrical and surface wave surveys are adopted. However, it is difficult to investigate time-based changes in under ground using these surveys. In contrast, surveys using cosmic-ray muons have been used to scan the inner parts of nuclear reactors with penetration technology. Surveys using muons enable real-time observation without the influence of vibration or electricity. Such surveys have great potential for available technology because of their ability to investigate density distributions without requiring as much labor. In this paper, survey technologies using cosmic ray muons are introduced, and the possibilities of applying such technologies as new physical survey technologies for underground structures are suggested.

• Journal of Korean Society of Archives and Records Management
• /
• v.22 no.1
• /
• pp.43-59
• /
• 2022

Electronic public records are classified simultaneously as production, a preservation period is granted, and after a certain period, they are transferred to an archive and preserved. This study intends to find a way to improve the efficiency in classifying transferred records and maintain consistent standards. To this end, the current record classification work process carried out by the National Archives of Korea was analyzed, and problems were identified. As a way to minimize the manual work of record classification by converging the required improvement, the process of identifying outlier candidates based on a list consisting of classified information of the transferred records was proposed and systemized. Furthermore, the proposed outlier discrimination process was applied to the actual records transferred to the National Archives of Korea. The results were standardized and constructed as a training data format that can be used for machine learning in the future.

• Journal of Internet Computing and Services
• /
• v.23 no.3
• /
• pp.35-45
• /
• 2022

Even in recent years, treatment of first-aid patients is still often delayed due to a shortage of medical resources in marginalized areas. Research on automating the analysis of medical data to solve the problems of inaccessibility for medical services and shortage of medical personnel is ongoing. Computer vision-based medical inspection automation requires a lot of cost in data collection and labeling for training purposes. These problems stand out in the works of classifying lesion that are rare, or pathological features and pathogenesis that are difficult to clearly define visually. Anomaly detection is attracting as a method that can significantly reduce the cost of data collection by adopting an unsupervised learning strategy. In this paper, we propose methods for detecting abnormal images on chest X-RAY images as follows based on existing anomaly detection techniques. (1) Normalize the brightness range of medical images resampled as optimal resolution. (2) Some feature vectors with high representative power are selected in set of patch features extracted as intermediate-level from lesion-free images. (3) Measure the difference from the feature vectors of lesion-free data selected based on the nearest neighbor search algorithm. The proposed system can simultaneously perform anomaly classification and localization for each image. In this paper, the anomaly detection performance of the proposed system for chest X-RAY images of PA projection is measured and presented by detailed conditions. We demonstrate effect of anomaly detection for medical images by showing 0.705 classification AUROC for random subset extracted from the PadChest dataset. The proposed system can be usefully used to improve the clinical diagnosis workflow of medical institutions, and can effectively support early diagnosis in medically poor area.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.381-391
• /
• 2022

This paper is intended to find one of the prevailing deep learning models that are a type of AI (Artificial Intelligence) that helps rapidly detect damaged buildings where disasters occur. The models selected are SSD-512, RetinaNet, and YOLOv3 which are widely used in object detection in recent years. These models are based on one-stage detector networks that are suitable for rapid object detection. These are often used for object detection due to their advantages in structure and high speed but not for damaged building detection in disaster management. In this study, we first trained each of the algorithms on xBD dataset that provides the post-disaster imagery with damage classification labels. Next, the three models are quantitatively evaluated with the mAP(mean Average Precision) and the FPS (Frames Per Second). The mAP of YOLOv3 is recorded at 34.39%, and the FPS reached 46. The mAP of RetinaNet recorded 36.06%, which is 1.67% higher than YOLOv3, but the FPS is one-third of YOLOv3. SSD-512 received significantly lower values than the results of YOLOv3 on two quantitative indicators. In a disaster situation, a rapid and precise investigation of damaged buildings is essential for effective disaster response. Accordingly, it is expected that the results obtained through this study can be effectively used for the rapid response in disaster management.

• Korean small business review
• /
• v.42 no.3
• /
• pp.1-25
• /
• 2020

To commemorate the 40th anniversary of the foundation of the Korean Association of Small Business Studies, this study reviewed research papers on the subject of entrepreneurship in the Asia Pacific Journal of Small Business. For 40 years, the subjects of entrepreneurship-related studies published in this journal were relatively limited and the number of articles was very few. The research papers mainly focus on defining entrepreneurship as an innovation or as a determinant of innovation and survey-based empirical studies have been conducted since the publication of the Entrepreneurial Orientation(EO) by Lumpkin and Dess(1996). Although entrepreneurship is a research field that can be approached from various perspectives such as economics, sociology, psychology, cultural anthropology, and organization theory, most of the papers published in the Asia Pacific Journal of Small Business do not clearly state their theoretical positions or viewpoints. Moreover, there are few studies that incorporate corporate entrepreneurs or startup teams although they have been major actors or entrepreneurship. Lastly, innovation has been the main focus of research, leaving other arenas such as opportunity recognition and discovery understudied. In order to increase the quantity and improve the quality in the entrepreneurship research, we need to have the entrepreneurship field as one academic section in the Asia Pacific Journal of Small Business.

• Journal of the Korean Electrochemical Society
• /
• v.25 no.4
• /
• pp.134-153
• /
• 2022

Regardless of a trade-off relationship between energy density and safety, it is essential to improve both properties for future lithium secondary batteries. Especially, to improve the energy density of batteries further, not only thickness but also weight of separators including ceramic coating layers should be reduced continuously apart from the development of high-capacity electrode active materials. For this purpose, an attempt to replace conventional slurry coating methods with a deposition one has attracted much attention for securing comparable thermal stability while minimizing the thickness and weight of ceramic coating layer in the separator. This review introduces state-of-the-art technology on ceramic-coated separators (CCSs) manufactured by the deposition method. There are three representative processes to form a ceramic coating layer as follows: chemical vapor deposition (CVD), atomic layer deposition (ALD), and physical vapor deposition (PVD). Herein, we summarized the principle and advantages/disadvantages of each deposition method. Furthermore, each CCS was analyzed and compared in terms of its mechanical and thermal properties, air permeability, ionic conductivity, and electrochemical performance.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.4D
• /
• pp.395-402
• /
• 2010

The seriousness of a traffic accident appears relatively higher on the curve sections compared with the straight sections due to a change in speed caused by a change in the driver's sight. In particular, the visual distortion phenomenon, one of the dangerous factors taking place on the curve sections, appears different according to the road's geometric design. Although it is a genuinely principal design factor which should be necessarily considered in designing a road, the previous researches on establishing the design standards for it have been insufficiently conducted. As a result, the establishment of the road design standards for the curve sections considering the sight distortion phenomenon is desperately required. This research examined the previous researches on the driver's behaviors, the driver's sight characteristics and the perceived curve radius on the curve sections, and developed the theoretical model of perceived curve radius to which a mathematical technique is applied in consideration of the visual distortion phenomenon on the two-lane curve sections in a local area. In addition, after the theoretical visual distortion was calculated on the basis of the theoretical model of perceived curve radius, the range of error on the theoretical recognition radius model formula was verified through comparing it with the previous researches' experiential visual distortion level and analyzing both of them. As a result, it was observed that as the curve radius practically increases in the theoretical recognition curve radius, the range of error tends to go down, which reflects well the characteristics of the curve sections on the road. Based on this research, it is expected that this research will be helpful to eliminate the safety defects when designing the curve sections and contribute to develop the road design standards considering human factors in the future.