• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.408-415
• /
• 2022

In this paper, we propose a 3D point cloud reconstruction technique from 2D images using efficient feature map extraction network. The originality of the method proposed in this paper is as follows. First, we use a new feature map extraction network that is about 27% efficient than existing techniques in terms of memory. The proposed network does not reduce the size to the middle of the deep learning network, so important information required for 3D point cloud reconstruction is not lost. We solved the memory increase problem caused by the non-reduced image size by reducing the number of channels and by efficiently configuring the deep learning network to be shallow. Second, by preserving the high-resolution features of the 2D image, the accuracy can be further improved than that of the conventional technique. The feature map extracted from the non-reduced image contains more detailed information than the existing method, which can further improve the reconstruction accuracy of the 3D point cloud. Third, we use a divergence loss that does not require shooting information. The fact that not only the 2D image but also the shooting angle is required for learning, the dataset must contain detailed information and it is a disadvantage that makes it difficult to construct the dataset. In this paper, the accuracy of the reconstruction of the 3D point cloud can be increased by increasing the diversity of information through randomness without additional shooting information. In order to objectively evaluate the performance of the proposed method, using the ShapeNet dataset and using the same method as in the comparative papers, the CD value of the method proposed in this paper is 5.87, the EMD value is 5.81, and the FLOPs value is 2.9G. It was calculated. On the other hand, the lower the CD and EMD values, the better the accuracy of the reconstructed 3D point cloud approaches the original. In addition, the lower the number of FLOPs, the less memory is required for the deep learning network. Therefore, the CD, EMD, and FLOPs performance evaluation results of the proposed method showed about 27% improvement in memory and 6.3% in terms of accuracy compared to the methods in other papers, demonstrating objective performance.

• Journal of the Korean Orthopaedic Association
• /
• v.55 no.4
• /
• pp.281-293
• /
• 2020

An anterior cruciate ligament (ACL) reconstruction is one of the most frequent surgical procedures in the knee joint, but despite the better understanding of anatomy and biomechanics, surgical reconstruction procedures still fail to restore rotational stability in 7%-16% of patients. Hence, many studies have attempted to identify the factors for rotational laxity, including the anterolateral ligament (ALL), but still showed controversies. Descriptions of the ALL anatomy are also confused by overlapping nomenclature, but it is usually known as a distinctive fiber running in an anteroinferior and oblique direction from the lateral epicondyle of the femur to the proximal anterolateral tibia, between the fibular head and Gerdy's tubercle. The importance of the ALL as a secondary restraint in the knee has been emphasized for successful ACL reconstructions that can restore rotational stability, but there is still some controversy. Some studies reported that the ALL could be a restraint to the tibial rotation, but not to anterior tibial translation. On the other hand, some studies reported that the role of ALL in rotational stability would be limited as a secondary structure because it bears loads only beyond normal biomechanical motion. The diagnosis of an ALL injury can be performed by a physical examination, radiology examination, and magnetic resonance imaging, but it should be assessed using a multimodal approach. Recently, ALL was considered one of the anterolateral complex structures, as well as the Kaplan fiber in the iliotibial band. Many studies have introduced many indications and treatment options, but there is still some debate. The treatment methods are introduced mainly as ALL reconstructions or lateral extra-articular tenodesis, which can achieve additional benefit to the knee stability. Further studies will be needed on the indications and proper surgical methods of ALL treatment.

• Korean Journal of Heritage: History & Science
• /
• v.55 no.3
• /
• pp.46-58
• /
• 2022

This study analyzed the documentation trend of garden components such as plants, infrastructure, unit facilities, and structures, based on 188 measurement drawings of 94 old houses in a report on the documentation of the national folklore cultural heritage. The findings are as follows. First, it was found that plants and structures continuously appeared as the subject of measurement drawings, while infrastructure was often omitted. It was confirmed that unit facilities, which are smaller than other components, were frequently excluded from the documentation subject as well due to frequent changes such as movement, loss, and expansion. Second, the level of expression in measurement drawings showed different aspects for each component. The unit facilities showed a large change over time with respect to the level of documentation, and the level of documentation was somewhat polarized, particularly toward the latter stage. This suggests that the level of documenting the drawings limited to specific facilities improved, but the overall level of drawings did not improve, such as a lack of diversification of expression techniques suitable for various unit facilities. On the other hand, it was confirmed that the level of documenting the drawings for plants, infrastructure and structures did not change to a significant degree, implying that no improvements were made to the expression of components. Third, as for the technique of detailed expression, in the case of plants, vegetation status was prepared without distinction of old or protected trees that have historical value. Above all, there was no record of the vegetation structure that could help grasp the vegetation landscape of the outer area. As for the infrastructure, there was no consistent expression technique to systematically convey topographic changes such as the height and slope of the land. In addition, since there was no subtype classification defined for unit facilities and structures, there was no subject or method of documentation. This study is meaningful in that it expanded the category of documentation, which has been concentrated on buildings in old houses, to gardens, and called attention to the need for documenting the gardens for the preservation and management of old houses as an integration of the building and outer area.

• Korean Journal of Environment and Ecology
• /
• v.37 no.4
• /
• pp.273-288
• /
• 2023

Although many studies have been conducted on techniques and effects that can be applied to forest meditation in domestic forest healing meditation research, there has been little research on the space where forest meditation takes place. Nevertheless, a meditation space is not just a place concept but a forest environment element responsible for the healing function of a forest, i.e., a place containing healing factors, and can be an essential clue to the healing mechanism. Therefore, to determine whether a healing forest meditation space is suitable for meditation, this study selected the attribute items of the meditation space using the Delphi expert survey and then surveyed the user satisfaction of the healing forest meditation space using the IPA (Importance Performance Analysis) technique. The survey was conducted from August to November 2022, targeting 315 adults who used the forest meditation space at the National Center for Forest Therapy, the Saneum Healing Forest, and the Jathyanggi Pureunsup Arboretum in Gyeonggi Province. The result of the IPA analysis showed the average satisfaction with the forest meditation space was relatively high at 4.33 points on a 5-point Likert scale (4.33 points for the National Center for Forest Therapy, 4.34 points for the Saneum Healing Forest, and 4.37 points for the Jathyanggi Pureunsup Arboretum), indicating that the three healing forest meditation spaces were suitable for forest meditation. Satisfaction with the "Sounds of nature" was high in all three forests. On the other hand, all three forests showed a relatively low satisfaction with "Quietness," indicating it to be a priority problem to be addressed. Also, an open-ended questionnaire survey showed that the mediation space's natural elements, such as natural sounds, scenery, air, forest spaces, and scents, had a higher positive impact on meditation satisfaction than artificial elements, such as facilities. Therefore, it is essential to secure sound resources such as the sound of water and birds around the meditation space, and it is also necessary to consider ways to create a meditation forest in an independent area to avoid encounters with visitors and allow only participants in the forest healing meditation program to enter to increase satisfaction with forest meditation.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Journal of the Korean Orthopaedic Association
• /
• v.54 no.1
• /
• pp.1-8
• /
• 2019

Globally, the elderly population is increasing rapidly, which means that the number of deformity correction operations for elderly spine deformity patient has increased. On the other hand, for aged patients with deformity correction operation, preoperative considerations to reduce the complications and predict a good clinical outcome are not completely understood. First, medical comorbidity needs to be evaluated preoperatively with the Cumulative Illness Rating Scale for Geriatrics or the Charlson Comorbidity Index scores. Medical comorbidities are associated with the postoperative complication rate. Managing these comorbidities preoperatively decreases the complications after a spine deformity correction operation. Second, bone densitometry need to be checked for osteoporosis. Many surgical techniques have been introduced to prevent the complications associated with posterior instrumentation for osteoporosis patients. The preoperative use of an osteogenesis inducing agent - teriparatide was also reported to reduce the complication rate. Third, total body sagittal alignment need to be considered. Many elderly spine deformity patients accompanied degenerative changes and deformities at their lower extremities. In addition, a compensation mechanism induces the deformed posture of the lower extremities. Recently, some authors introduced a parameter including total body sagittal alignment, which can predict the clinical outcome better than previous parameters limited to the spine or pelvis. As a result, total body sagittal alignment needs to be considered for elderly spine deformity patients after a deformity correction operation. In conclusion, for elderly spine deformity patients, medical comorbidities and osteoporosis need to be evaluated and managed preoperatively to reduce the complication rate. In addition, total body sagittal alignment needs to be considered, which is associated with better clinical outcomes than the previous parameters limited to the spine or pelvis.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.41 no.4
• /
• pp.21-29
• /
• 2023

The Northern Song Dynasty, the heyday of cultural and artistic achievements, brought significant changes to the history of gardens in China. The developments and contemplations that had evolved during the previous Tang Dynasty became intertwined with literature, painting, and art, leading to garden being perceived as works of art. In particular, the emergence of Su Shi(蘇軾) that permeated literature and art during the Northern Song Dynasty, had an impact beyond individual garden creation, influencing the development of public gardens and the diversification of garden. His long exile periods served as an opportunity to understand and reflect the local culture and characteristics, influencing the development of the garden. This study focuses on the ideology of Su Shi(蘇軾) that managed various gardens, examining the relationship between his exlie life and ideology. To do so, the study examines the form of the literati's gardens managed by Su Shi(蘇軾), with a particular emphasis on the Baiheju(白鶴居) garden in Huizhou, revealing the following characteristics and values. First, Su Shi(蘇軾), who was proficient in the Three Houses: Confucianism, Buddhism, and Taoism, combined his philosophy and unique perspective techniques with the location and composition elements of Baiheju(白鶴居) to enjoy the landscape. Although the ancient residence has a simple form, it possesses expansiveness through the combination of internal and external views. The interior is designed to be perceived as a single space, but it allows overlapping experiences of space and simultaneous appreciation of different sceneries. On the other hand, the spatial layout incorporates a hierarchical order to establish a sense of order. Second, the garden reflects the local characteristics, featuring numerous tropical plants and presenting vibrant and contrasting colors with structures. The planting forms embrace the concept of "huosei seikou" (活色生香) to enhance the color harmoniously. Additionally, the garden incorporates the poet's spiritual world, projecting it onto the garden as a contemplative place for spiritual nourishment and exploration of the ideal realm. For the pursuit of serenity and profound contemplation, the selected plantings are simple yet distinctive, providing rhythm and depth to the garden space. Third, Baiheju(白鶴居) has undergone changes over the years, but fundamentally, the form and elements of the garden shaped by Su Shi(蘇軾)'s descendants persist, confirming its heritage value.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.25 no.2
• /
• pp.79-92
• /
• 1992

This study was carried out to develop new techniques useful for cryopreservation, thawing and artificial insemination, and ultrastructural changes of cryopreserved spermatozoa in rainbow trout(Oncorhynchus mykiss) . Two extenders, such as Tyrode solution and Whittingham's $T_6$ solution, were used to preserve rainbow trout sperm in refrigerator $(-20,\;-40\;and\;-70^{\circ}C)$ or liquid nitrogen $%(-196^{\circ})$. Hand-stripped semen was diluted to 1:16 with two extenders, an then the semen were frozen after mixing semen and each extender containing 1M or 1.5M DMSO solution to 1:1. After 60 days cryopreserved semen was thawed in a $13^{\circ}$ water bath, and subsequently centrifugated. After centrifugation at 1,000 rpm for 5 min thawed semen was washed with extenders, and then fertilized with fresh eggs. The results obtained in these experiments were summarized as follows: After cryopreservation, over 75% of spermatozoa were appeared motile and the survival rate was high. Following cryopreservation by the addition of cryoprotectant such as DMSO, methanol and glycerol, the fertilization rate of the thawed spermatozoa appeared over $99\%$ compared with the control having $99\%$ of fertilization rate. There was no difference between the control and experimental groups such as $(-20^{\circ}C\;-40^{\circ}C\;and\;-70^{\circ}C)$ and $-196^{\circ}$ in fertilization rate. Following cryopreservation at $-196^{\circ}$ by the addition of 1M DMSO of cryoprotectant, each fertilization rate following 24 hours and hatching rate following 24 days showed $96\%$ and $8\%$ by the addition of BSA, but showed $98\%\;and\;10%$ by no addition of BSA. Following 2 months of cryopreservation by the addition of 1M DMSO of cryoprotectant, there were $10%$ of hatching rate at $-196^{\circ}\;and\;10\%\;and\;35\%,\;respectively,\;at\;-40^{\circ}C\;and\;-70^{\circ}C$. Following 2 months of cryopreservation by the addition of 1M methanol of cryoprotectant, there were $22\%$ of fertilization rate at $-20^{\circ}C,\;and\;28\%,\;at\;-70^{\circ}C$ Following 2 months of cryopreservation by the addition of 1M glycerol of cryoprotectant, there were $22\%$ of fertilization rate at $-20^{\circ}C$, and $33\%,\;at\;-70^{\circ}C$. pollowing 2 months of cryopreservation by the addition of 1.5M DMSO of cryoprotectant, there were $27\%$ of fertilization rate at $-20^{\circ}C,\;an\;36\%\;and \;35\%,\;respectively,\;at\;-40^{\circ}C\;and\;-70^{\circ}C$. Following 2 months of cryopreservation by the addition of 1.5M glycerol of cryoprotectant, there were $34\% \;of\;fertilization\;rate\;at\;-20^{\circ}C, \;and\;31\%\;and\;31\%,\;respectively,\;at \;-40^{\circ}C\;and\;-70^{\circ}$. Following 2 months of cryopreservation by the addition of 1.5M methanol of cryoprotectant, there were $28\%$ of fertilization rate at $-20^{\circ}C,\;and\;29\%\;and\;28\%,\;respectively,\;at\;-40^{\circ}C\;and\;-70^{\circ}C.$ From 10 days and 15 days following fertilization at $13^{\circ}C\;and\;10^{\circ}C$, respectively, the mortality rate of fertilized ova was markedly increased. The middle piece of spermatozoa had two set of central doublets, nine set of outer coarse fibres, and mitochondrial sheath. Spermatozoa went through morphological changes during storage, e.g. winding of flagella, detachment of the nuclear envelope and the plasma membrane from the nucleus of the sperm head. There were $1\%$ abnormal spermatozoa in fresh sperm and about $15\%$ during storage.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.18 no.2
• /
• pp.149-156
• /
• 1985

Distribution of lipid components in the tissue of meat, skin and viscera from carp(Cyprynus carpio) was analyzed using the techniques of column chromatography, thin layer chromatography and gas liquid chromatography according to the previous report(Choi, et al., 1984). Lipid content was varied by the portion such as $3.88\%$ in meat (free lipid, $2.47\%$ ; bound lipid, $1.41\%$), $8.02\%$ in skin(free lipid, $5.65\%$ ; bound lipid, $2.37\%$) and $6.18\%$ in viscera (free lipid, $3.54\%$ ; bound lipid, $2.64\%$). In the all portions of the body, free lipid was composed of $68\%\;to\;92\%$ in neutral lipid, $3\%\;to\;6\%$ in glycolipid and $4\%\;to\;18\%$ in phospholipid whereas bound lipid was composed of $8\%\;to\;20\%$ in neutral lipid, $2\%\;to\;7\%$ in glycolipid and $47\%\;to\;62\%$ in phospholipid. The free lipids of the tissues on the each portion were mostly represented by triglycerides and some diglycerides, but free lipids in viscera contained considerable amounts of free fatty acids. The bound lipids, on the other hand, commonly comprised appreciable amounts of esterified sterol and hydrocarbon, and triglycerides. The phospholipid was mainly consisted of phosphatidyl choline, phosphatidyl ethanolamine and phosphatidyl serine in the both free and bound lipids, and much more phosphatidyl choline in the bound lipid. The predominant fatty acids of free and bound lipids were $C_{16:0},\;C_{18:0},\;C_{20:4},\;C_{22:6}\;and\;C_{18:2}$ acids in polar lipids, and $C_{16:0},\;C_{16:1},\;C_{18:0},\;C_{18:1}\;and\;C_{18:2}$ acids in non-polar lipids, whereas those of neutral lipids were $C_{14:0}(2.54{\sim}6.98\%),\;C_{16:0}(11.20{\sim}21.13\%)$ and $C_{18:0}(1.58{\sim}12.76\%)$ of saturated acids, $C_{16:1}(7.06{\sim}20.70\%),\;C_{18:1}(21.68{\sim}30.50\%)$ and $C_{20:1}(1.76{\sim}6.27\%)$ of monoenoic acids, and $C_{18:2}(4.50{\sim}6.89\%),\;C_{20:4}(1.52{\sim}4.29\%)$ and $C_{22:6}(0.73{\sim}6.62\%)$, respectively. In conclusion, the fatty acid compositions revealed apparent differences between the free lipid and bound lipids in the tissues of body.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.191-204
• /
• 2015

According to the '2013 Performance Assessment Report on the Financial Program' from the National Assembly Budget Office, the unfilled recruitment ratio of Software(SW) Developers in South Korea was 25% in the 2012 fiscal year. Moreover, the unfilled recruitment ratio of highly-qualified SW developers reaches almost 80%. This phenomenon is intensified in small and medium enterprises consisting of less than 300 employees. Young job-seekers in South Korea are increasingly avoiding becoming a SW developer and even the current SW developers want to change careers, which hinders the national development of IT industries. The Korean government has recently realized the problem and implemented policies to foster young SW developers. Due to this effort, it has become easier to find young SW developers at the beginning-level. However, it is still hard to recruit highly-qualified SW developers for many IT companies. This is because in order to become a SW developing expert, having a long term experiences are important. Thus, improving job continuity intentions of current SW developers is more important than fostering new SW developers. Therefore, this study surveyed the job continuity intentions of SW developers and analyzed the factors associated with them. As a method, we carried out a survey from September 2014 to October 2014, which was targeted on 130 SW developers who were working in IT industries in South Korea. We gathered the demographic information and characteristics of the respondents, work environments of a SW industry, and social positions for SW developers. Afterward, a regression analysis and a decision tree method were performed to analyze the data. These two methods are widely used data mining techniques, which have explanation ability and are mutually complementary. We first performed a linear regression method to find the important factors assaociated with a job continuity intension of SW developers. The result showed that an 'expected age' to work as a SW developer were the most significant factor associated with the job continuity intention. We supposed that the major cause of this phenomenon is the structural problem of IT industries in South Korea, which requires SW developers to change the work field from developing area to management as they are promoted. Also, a 'motivation' to become a SW developer and a 'personality (introverted tendency)' of a SW developer are highly importantly factors associated with the job continuity intention. Next, the decision tree method was performed to extract the characteristics of highly motivated developers and the low motivated ones. We used well-known C4.5 algorithm for decision tree analysis. The results showed that 'motivation', 'personality', and 'expected age' were also important factors influencing the job continuity intentions, which was similar to the results of the regression analysis. In addition to that, the 'ability to learn' new technology was a crucial factor for the decision rules of job continuity. In other words, a person with high ability to learn new technology tends to work as a SW developer for a longer period of time. The decision rule also showed that a 'social position' of SW developers and a 'prospect' of SW industry were minor factors influencing job continuity intensions. On the other hand, 'type of an employment (regular position/ non-regular position)' and 'type of company (ordering company/ service providing company)' did not affect the job continuity intension in both methods. In this research, we demonstrated the job continuity intentions of SW developers, who were actually working at IT companies in South Korea, and we analyzed the factors associated with them. These results can be used for human resource management in many IT companies when recruiting or fostering highly-qualified SW experts. It can also help to build SW developer fostering policy and to solve the problem of unfilled recruitment of SW Developers in South Korea.