• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.8
• /
• pp.311-318
• /
• 2021

Research has been ongoing to detect ships from offshore photographs for a variety of reasons, including maritime security, identifying international trends, and social scientific research. Due to the development of artificial intelligence, R-CNN models for object detection in photographs and images have emerged, and the performance of object detection has risen dramatically. Ship detection in offshore photographs using the R-CNN model has also begun to apply to satellite photography. However, satellite images project large areas, so various objects such as vehicles, landforms, and buildings are sometimes recognized as ships. In this paper, we propose a novel methodology to improve the performance of ship detection in satellite photographs using R-CNN series models. We separate land and sea via marker-based watershed algorithm and perform morphology operations to specify RoI one more time, then detect vessels using R-CNN family models on specific RoI to reduce typology. Using this method, we could reduce the misdetection rate by 80% compared to using only the Fast R-CNN.

• Journal of Digital Convergence
• /
• v.17 no.11
• /
• pp.183-188
• /
• 2019

As social perceptions of pets change, cultural attitudes toward pets are becoming more friendly. In particular, dogs have been living familiarly and closely with humans for a long time. In the changing times, various services are being used to improve the understanding of dogs and to prevent companion dogs and increase awareness of respect for life. Therefore, in this paper, we implemented a smart lead line in which IoT service and application technology are linked to the walking dog's automatic lead line. To do this, we developed a smart dog lead line by designing and implementing an integrated module in connection with heterogeneous sensors and linking it with a dog lead line. Finally, a smart dog lead line was used to collect the dog's biological signals in real time, identify the location of the dog, and provide a notification system. Through this, we believe that the culture of dog culture can be further grown.

• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.6_2
• /
• pp.1043-1050
• /
• 2020

In this study, a study was presented on the monitoring technique of landslide area using UAV. In the case of disaster investigation using drone mapping, it can be used at various disaster sites. The mission can be carried out at various disaster sites, including surveys of damage to mountainous areas caused by landslides, building collapses surveys of flood damage, typhoons, earthquakes. The damage investigation plan using drone mapping is expected to be highly utilized at disaster sites where investigators cannot access it like in mountainous areas and where it is difficult to conduct direct damage investigations at the site. Drone mapping technology has many advantages in terms of disaster follow-up, such as recovery. Compared to the existing survey system, which was mainly carried out manually, the investigation time can be drastically reduced, and it can also respond to disaster sites that are difficult to carry out or are difficult to access directly. In addition, it is possible to establish and guide spatial data at the disaster site based on accurate mapping data from the time of the disaster, which has considerable strength in managing the situation of the disaster site, selecting priority areas for recovery, and establishing recovery plans. As such, drone mapping is a technology that can be used in a wide range of sites along with natural disasters and social disasters. If a damage investigation system is established through this, it is believed that it will contribute significantly to the rapid establishment of recovery plans along with the investigation of disaster response time and extent of damage recovery.

• Journal of the Korea Convergence Society
• /
• v.12 no.6
• /
• pp.139-150
• /
• 2021

Currently, the RPS(Renewable Portfolio Standard) is the policy which supplies new and renewable energy. Power generation companies with large capacity should produce renewable energy or secure through the purchase of REC (Renewable Energy Certificates) as mandatory. The government has revised the REC weight several times, which weights each energy source by evaluating the economic and social value of renewable energy sources, and revised the mandatory supply ratio to gradually increase. This study helps to find the impact of policies on related industries. In this study, time-series analysis and regression analysis on the capacity of PV(Photovoltaics) facilities as a dependent variable were performed to analyze the effect of the revision of the REC weight for photovoltaic power generation and the amount of mandatory supply for renewable energy. As a result, it was statistically assessed that the revision of the REC weight and the increase in the mandatory supply has a significant effect on the increase in the amount of PV facilities.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.34 no.5
• /
• pp.97-108
• /
• 2018

"Death is the side of life which is turned away from us." The life of people in Seoul, however, is disconnected from death. Why? This article compares the historical changes in the cemetery disposition of Paris and Seoul to answer this question. The cemetery is always a meeting place between the living and the dead. In pre-modern cities, the cemetery was close to the people's daily life. However, the fundamental change of urban structure due to modernization has a great influence on the cemetery. With the advent of the train, the world has shrunk and the city has expanded unprecedentedly. In such a situation, the cemetery is expelled to the outside of the city. However, while Paris and Seoul share the same overall flow, they responded differently to the plans for the establishment of large-scale remote cemeteries. In Paris, the plan was canceled by citizens who value their relationship with the dead. On the other hand, Seoul was unable to manage the cemetery due to social confusion in 20th century. All cemeteries were expelled as industrialization began. As a result, there is no public cemetery or ossuary at present in Seoul. In Seoul, about 20 years ago however, a new kind of place for the dead began to appear. It is an ossuary attached to religious facilities. In other words, the current cemetery of Seoul is divided into two forms : the public cemetery, which is expelled from the city, and the private ossuary, which is attached to religious facilities built in the city.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.35 no.4
• /
• pp.3-14
• /
• 2019

The purpose of this study is to analyze the distribution characteristics of the agency-managed shared housings in Seoul and draw the possible implications from it. The needed data for the study was obtained from an on-line shared housing portal service which provides housing information from various shared housing management agencies. By mapping out the locations and other related data into a GIS(Geographic Information System) program, this study shows that shared housings in Seoul can be sorted into four large clusters. Each cluster has a different ratio of housing types and room capacities reflecting each regional circumstance and common causes. Women-only shared housing takes up 79% of the overall shared housing ratio and, while multi-family housing type has the most count, the apartment type has a noticeably high ratio in women-only housing compared to the apartment type ratio among the other gender-specific housings. Given the high crime rate against the single-person household of young adult women, the reason for the popularity of shared-apartment housing among young women can be deduced. However, the potential tenants' practical choices and their concern for safety are not the only causes that drive the current shared housing market. The young adults in their 20's and 30's choose to live in popular places where they can engage social activities. A new tier of shared housing market has also appeared in places where young adults could not have afforded if they lived alone. Choosing where we live is no longer about just meeting the requirements for a house based on what she/he needs but also about satisfying the preferences for a living based on what she/he desires. This paper indicates that although there is an undeniable premise that 'sharing a house' revolves around the realm of housing welfare and is not a typical topic for the upper-income households, the way we live and how we choose our place to live is shifting.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.35 no.7
• /
• pp.119-126
• /
• 2019

The active living of the elderly leads to improve their lives and enhance social networks. In the view of the active living, the walkability is an essential factor for the elderly's daily life. To support the active living, making age-friendly environment is important. Considering that the elderly mainly carry out activities through walking, making the age-friendly walking environment is a preliminary action. The existing studies applied various methods such as surveys by experts. In spite of the benefits in theirs, there is still a limitation that current walkability measurement methods did not incorporate the actual elderly's walking activity. Thus, the purposes of this study is to measure the elderly's walking quantitatively using a wearable sensor, and to investigate the feasibility of comparing several walking environments based on the data collected from the actual elderly's walking. To do this, experiment was conducted in four types environments with 22 senior subjects. The walkability was measured by walking stability represented quantitatively as Maximum Lyapunov Exponent (MaxLE). Through the experiment results, it was confirmed that the stability of the elderly walking was different according to the walking environment, which also meant that bodily responses (walking stability) is highly related to walkability. The results will provide an opportunity for the continuous diagnosis of walking environments, thereby enhancing the active living of the elderly.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.36 no.3
• /
• pp.49-58
• /
• 2020

Based on Merrill's instructional theory, this study pursued to develop a demonstration-based architectural design class operation model for the 3^rd year undergraduate students taking a Spring semester design studio class. The model was designed and used particularly to improve architectural thinking abilities of under-motivated learners. Learning effects of the model were examined based on the preliminary data obtained for 3 consecutive years, 2017 through 2019. A total of 52 students were participated in the class and observed by the instructor. Once developed, the model has been continually updated and improved based on results of each class operation. Five types of demo. were used in the model. First, direct contacts of the instructor with under-motivated learners were turned out to be the most preferred demo(demo. 4), while watching and listening of the demo(demo.3) between the instructor and motivated learners taking place in class was ranked at the second place. Belief of under-motivated learners on the instructor as a professional should be highly valued for improving their architectural thinking abilities. Second, motivated peers' direct help for under-motivated ones was placed in the third rank. Social attitudes of under-motivated learners towards accepting motivated ones' helps were determined the particular demo's appropriateness. Third, a set of guidelines for operating the model in undergraduate design studio classes were developed and suggested.

• Journal of Ocean Engineering and Technology
• /
• v.35 no.1
• /
• pp.91-97
• /
• 2021

Marine accidents caused by ships have brought about economic and social losses as well as human casualties. Most of these accidents are caused by small and medium-sized ships and are due to their poor conditions and insufficient equipment compared with larger vessels. Measures are quickly needed to improve the conditions. This paper discusses a video-integrated collision prediction and fall detection system to support the safe navigation of small- and medium-sized ships. The system predicts the collision of ships and detects falls by crew members using the CCTV, displays the analyzed integrated information using automatic identification system (AIS) messages, and provides alerts for the risks identified. The design consists of an object recognition algorithm, interface module, integrated display module, collision prediction and fall detection module, and an alarm management module. For the basic research, we implemented a deep learning algorithm to recognize the ship and crew from images, and an interface module to manage messages from AIS. To verify the implemented algorithm, we conducted tests using 120 images. Object recognition performance is calculated as mAP by comparing the pre-defined object with the object recognized through the algorithms. As results, the object recognition performance of the ship and the crew were approximately 50.44 mAP and 46.76 mAP each. The interface module showed that messages from the installed AIS were accurately converted according to the international standard. Therefore, we implemented an object recognition algorithm and interface module in the designed collision prediction and fall detection system and validated their usability with testing.

• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.29-41
• /
• 2021

Recently, there are increasing attempts to utilize deep learning methodology in the fashion industry. Accordingly, research dealing with various fashion-related problems have been proposed, and superior performances have been achieved. However, the studies for fashion style classification have not reflected the characteristics of the fashion style that one outfit can include multiple styles simultaneously. Therefore, we aim to solve the multi-label classification problem by utilizing the dependencies between the styles. A multi-label recognition model based on a graph convolution network is applied to detect and explore fashion styles' dependencies. Furthermore, we accelerate model training and improve the model's performance through transfer learning. The proposed model was verified by a dataset collected from social network services and outperformed baselines.