• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.313-315
• /
• 2017

Recently, application fields using machine learning have been widely expanded. In addition to the spread of smart devices, application services using location-based services are also in demand. However, it is difficult to provide the application service through the positioning in the indoor environment such as the specific space where the disaster situation where the information for positioning can not be collected and the actual location location information can not be used. In this situation, using the spatial information composed of the marker information and the markers of the neighbor registered in the augmented reality environment, positioning at a specific situation or position becomes possible. At this time, it is possible to learn the operation that makes the configuration of the marker-based spatial information correspond to the actual position through the machine learning, and the optimal positioning result can be obtained by minimizing the error. In this paper, we study the positioning methods required in specific situations using machine learning for learning of augmented reality markers and spatial information.

• Journal of KIISE
• /
• v.43 no.7
• /
• pp.795-800
• /
• 2016

In image classification, recent CNNs compete with human performance. However, there are limitations in more general recognition. Herein we deal with indoor images that contain too much information to be directly processed and require information reduction before recognition. To reduce the amount of data processing, typically variational inference or variational Bayesian methods are suggested for object detection. However, these methods suffer from the difficulty of marginalizing over the given space. In this study, we propose an image-text integrated recognition system using active vision based on Spatial Transformer Networks. The system attempts to efficiently sample a partial region of a given image for a given language information. Our experimental results demonstrate a significant improvement over traditional approaches. We also discuss the results of qualitative analysis of sampled images, model characteristics, and its limitations.

• Fire Science and Engineering
• /
• v.32 no.3
• /
• pp.95-107
• /
• 2018

This study analyzed the working conditions of the fire protection system in the Goyang Bus Terminal fire based on the fire investigation results. The results were as follows. First, extinguishing using an indoor fire hydrant was not attempted immediately after the fire burned the ceiling urethane foam. Second, a sprinkler alarm valve was turn off and did not work in the repair work space of the 1st basement. On the other hand, the sprinklers in the $2^{nd}$ basement, $1^{st}$ floor, $2^{nd}$ floor, and $3^{rd}$ floor worked and prevented the fire from moving to stories other than the $1^{st}$ basement. Third, although an exit light worked normally, it was not installed in the exit from the waiting room in the $2^{nd}$ floor to the bus stop. This resulted in many casualties. Fourth, although a fire receiver sent an electrical signal to the fan controller of the smoke control system, it was treated manually in the fan controller and the fan in the $2^{nd}$ floor did not work.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.12
• /
• pp.1691-1697
• /
• 2018

There has been a steady study of unmanned vehicle. So far, continuous research has brought news of the commercialization of unmanned vehicle. In addition, it has been applied in a variety of fields with another industry. A lot of research has been done, too, to apply inert driving indoors. Using LoRa network, which is a network dedicated to IoT, unmanned vehicle control system that is applied to LoRa network from a small space, or from an office hospital to a factory, is installed to increase efficiency when the performs special tasks. This paper presents solutions to a variety of problems by using LoRa network, which is dedicated to IoT, to recognize an unmanned vehicle as a single object, to communicate with surrounding objects, and to receive information necessary for driving indoors from a cloud server.

• The Journal of the Korea Contents Association
• /
• v.21 no.10
• /
• pp.264-273
• /
• 2021

To study how digital content can be effectively developed and transformed in a post-COVID world in which the normal operations of museums have been disrupted, this paper analyzes the rapid development and limitations of VR exhibitions and proposes, as an alternative, the development of AR exhibitions. Studying VR/AR exhibitions that ran before and after COVID-19, this paper finds that VR, on the one hand, translates physical objects into digital video, which lacks aesthetic depth, and encounters operational problems originated by devices. By using mobile devices that are widely distributed and convenient to use, AR exhibitions can, on the other hand, be divided into three types: "museum-specific exhibitions" can present digital content in a specific indoor space, while "place-specific exhibitions" can be used in open outdoor spaces. The "non-place-specific exhibitions", can, as third type, combine digital content with printed material sent by postal mail. Among these three types, the specific/unspecified place type shows the highest "uncontact effect," which can suggest the best direction for effective museum content development in the pandemic era.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.7
• /
• pp.935-941
• /
• 2020

People estimation is important to provide IoT services. Most people counting technologies use camera or sensor data. However, the conventional technologies have the disadvantages of invasion of privacy and the need to install extra infrastructure. This paper proposes a method for estimating the number of people using a Wi-Fi AP. We use channel state information of Wi-Fi and analyze that using deep learning technology. It can be achieved by pre-installed Wi-Fi infrastructure that reduce cost for people estimation and privacy infringement. The proposed algorithm uses a k-binding data for pre-processing process and a 1D-CNN learning model. Two APs were installed to analyze the estimation results of six people. The result of the accurate number estimation was 64.8%, but the result of classifying the number of people into classes showed a high result of 84.5%. This algorithm is expected to be applicable to estimate the density of people in a small space.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.50-56
• /
• 2021

This study examines 3D scanning and how it is used in the construction field. 3D scanning technology was applied to a real space and compared with drawings in the planning and construction stages. 3D scanning technology has been widely applied in the field of construction, design, construction, and safety. The results of comparing 3D scanning data with drawings are as follows. First, the external shape and dimensions do not show much difference. Second, the internal shape and dimensions are different. Third, indoor lighting layouts are different in all buildings. 3D scanning should be an essential element in the construction stage before completion and should be used for supervision tasks such as material management, improving the efficiency of construction, and safety management through continuous 3D scanning using automation and robots. Follow-up studies in the field of architecture, such as BIM and process management, will be needed.

• Particle and aerosol research
• /
• v.18 no.1
• /
• pp.1-8
• /
• 2022

Since 2019, the corona virus has been continuously affect human life. In particular, in the indoor space where people live, infection by airborne transmission of viruses is a problem. Among them, the spread in the subway, which is the main mode of transport for humans, can be serious. To solve this problem, our research team developed an ionic wind collector to collect and remove corona virus using an ionic wind collector and ozone. In order to apply the ionic wind collector to the subway, it must operate in two modes. Because large amounts of ozone are harmful to the human body. There is a mode that collects bio-aerosol from the air using ionic wind and a mode that inactivates viruses floating in the air by generating a large amount of ozone. As the applied voltage increased, the cleaning ability of the ionic wind collector increased, and the farther the distance between the discharge electrode and the ground plate, the higher the cleaning ability even at low current. In addition, clean air delivery rate (CADR) of an ionic wind collector was up to 5.5 m³/min. As a result of measuring the amount of ozone generated, it was confirmed that 50 ppb to 250 ppb was generated, and it was confirmed that ozone generation was controllable in the ionic wind dust collector.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.45-52
• /
• 2022

A tangible sports game is an exercise game that uses sensors or cameras to track the user's body movements and to feel a sense of reality. Recently, VR indoor sports room systems installed to utilize tangible sports game for physical activity in schools. However, these systems primarily use screen-touch user interaction. In this research, we developed a V-Catch Vision system that uses AI image recognition technology to enable tracking of user movements in three-dimensional space rather than two-dimensional wall touch interaction. We also conducted a usability evaluation experiment to investigate the exercise effects of this system. We tried to evaluate quantitative exercise effects by measuring blood oxygen saturation level, the real-time ECG heart rate variability, and user body movement and angle change of Kinect skeleton. The experiment result showed that there was a statistically significant increase in heart rate and an increase in the amount of body movement when using the V-Catch Vision system. In the subjective evaluation, most subjects found the exercise using this system fun and satisfactory.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.139-146
• /
• 2022

Mountain accidents such as forest fires and missing people are increasing as hikers increase due to indoor activities restrictions caused by the prolonged COVID-19 incident. If a dangerous situation occurs at outside where rescue workers cannot reach, the search time for person can be reduced using a quadcopter. Considering this, in this paper, Multiwii is used to smoothly hover the quadcopter by setting optimized PID values of the x-axis, y-axis, and z-axis (Yaw) according to the change in the inclination of the gas. In addition, after installing Open CV on Raspberry Pie, the camera uses HSV color space to filter the color such as the description of the person, and uses a thermal imaging camera to receive thermal sensing images in real time in environments where color extraction is difficult. As a result, it was confirmed that hovering was possible at a height of 2 to 8 m, blue extraction was possible at a height of 5 m, and heat detection was possible at a distance of less than 10 cm.