• Journal of Korea Technology Innovation Society
• /
• v.20 no.4
• /
• pp.1036-1056
• /
• 2017

The rapid increase of ageing population and chronic disease patients cause high medical expenses, and it led an increased attention to digital healthcare. Smart car technologies for healthcare have been developing to recognize drivers' status and predict diverse driving environments. The present study aimed to understand the research trends of autonomous vehicle technologies of Korea and the United States through time series analysis, network analysis, visualization, and comparison between the two countries. The results suggest that cooperative study needs to be done in common research areas such as driver's safety and algorithms. It is also needed to conduct studies and benchmark about liking technique related to part-to-part and vehicle-to-vehicle as America's competitive advantaged area. In the US, diverse approaches of autonomous vehicle technologies have used to consider the characteristics of various age groups and passengers' health status through sensor, while in Korea, only one aspect, older drivers, is mentioned. Implications for the development direction of autonomous vehicle technologies with competitiveness in considering public health, ethics, and driver's safety and convenience are discussed in detail.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.130-136
• /
• 2016

In this paper, the real time monitoring system for the abnormal state of marine algae does not detect the plankton which may directly cause the red tide or the water bloom. But checks both oxygen reduction and nitrogen reduction in water, which indicates the characteristics of zooplankton and phytoplankton respectively, and this system makes a module that monitors in real time the temperature and the illumination of the water, which are indirect factors, with sensors placed in and outside the water, and this module transmits signals periodically at specific intervals to a sever that builds up data base, and the data collected in these ways will be analyzed and compared with the standard data from Ministry of Oceans and Fisheries, and then these data will be made the adequate form of information to be provided to the users as visual information, thus, this system intends to make a red tide and water bloom monitoring system tailored for individual fish farm businesses that has local characteristics and can quickly operate outside working hours, which differs from the existing wide area detecting and monitoring systems.

• The KIPS Transactions:PartD
• /
• v.16D no.2
• /
• pp.249-256
• /
• 2009

This paper introduces an efficient USN (ubiquitous sensor network) for monitoring blind areas in a skiing resort, developed as a part of u-Sport showcase project of Gangwon Province. Blind areas of a skiing resort are dangerous and/or steep areas located aroud ski slopes, which are rarely traveled and not easily seen by a ski patrol. If an accident occurs in such a blind area, the main control center of the sking resort can hardly recognize the accident and provide first aid and rescue services promptly. The blind area monitoring system proposed in this paper monitors a blind area of a skiing resort using five battery-powered sensor nodes each of which has an image sensor on it and wirelessly transmits images around the blind area to the main control center on a regular basis, therebly allowing real-time monitoring of the blind area and prompt rescue services in case of accidents. Additionally, the monitoring system provides an emergency button which skiers injured in the blind area can push. If the button is pushed, an image around the button and an alarm signal are transmitted to the main control center and therefore the main control center can take prompt actions for rescuing the injured skiers.

• Korean Journal of Remote Sensing
• /
• v.22 no.4
• /
• pp.275-284
• /
• 2006

The noise sources of a Hyperion image are mainly due to the atmospheric effects, the sensor's instrumental errors, and A/D conversion. Though uncalibrated, overlapping, and all deep water absorption bands generally are removed, there still exist noisy bands. The visual inspection for selecting clean and stable processing bands is a simple practice, but is a manual, inefficient, and subjective process. In this paper, we propose that the extrema ratio be used for noise estimation and unsupervised band selection. The extrema ratio was compared with existing SNR and entropy measures. First, Gaussian, salt and pepper, and Speckle noises were added to ALI (Advanced Land Imager) images with relatively low noises, and the relation of noise level and those measures was explored. Second, the unsupervised band selection was performed through the EM (Expectation-Maximization) algorithm of the measures which were extracted from a Hyperion images. The Hyperion data were classified into 5 categories according to the image quality by visual inspection, and used as the reference data. The experimental result showed that the extrema ratio could be used effectively for band selection of Hyperion images.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.219-227
• /
• 2019

Manufacturing methods have been changed from labor-intensive methods to technological intensive methods centered on manufacturing facilities. As manufacturing facilities replace human labour, the importance of monitoring and managing manufacturing facilities is emphasized. In addition, Big Data technology has recently emerged as an important technology to discover new value from limited data. Therefore, changes in manufacturing industries have increased the need for smart factory that combines IoT, information and communication technologies, sensor data, and big data. In this paper, we present strategies for existing domestic manufacturing factory to becom big data based smart-factory through technologies for distributed storage and processing of manufacturing facility data in MongoDB in real time and visualization using R programming.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.10
• /
• pp.429-438
• /
• 2021

In recent, realistic content has been applied in various ways due to the development of display technology and hologram, the final realistic content technology, have been used limitedly in accordance with the growing public demand. However, most realistic content requires additional devices of HMD (head mounted device) or glasses type, and other realistic content display technologies deliver a single image plane in the experience space to the user, providing a monotonous content experience. Various realistic contents with hologram technology are introduced in this work. In addition, we propose an interaction based realistic hologram service based that combines projection mapping and floating holograms. Projection-mapped screens and multi-floating hologram device provide a three-dimensional volumetric space with extended depth orientation from the user's point of view, while allowing users' entire and partial motions to be recognizable through multiple sensors.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.6
• /
• pp.60-71
• /
• 2019

As IoT systems such as smart farms and smart cities become popular, a large amount of data collected from many sensor nodes is sent to a server in the Internet, which causes network traffic explosion, delay in delivery, and increase of server's workload. To solve these problems, the concept of fog computing has been proposed to store data between IoT systems and servers. In this study, we implemented a software platform of the fog node and applied it to the prototype smart farm system in order to check whether the problems listed above can be solved when using the fog node. When the fog node is used, the time taken to control an IoT device is lower than the response time of the existing IoT device-server case. We confirmed that it can also solve the problem of the Internet traffic explosion and the workload increase in the server. We also showed that the intelligent control of IoT system is feasible by having the data visualization in the server and real time remote control, emergency notification in the fog node as well as data storage which is the basic capability of the fog node.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.854-856
• /
• 2016

Nowadays, the interests about medical service and health concerting, in other words "Healthcare",are increasing. For healthcare, one of the most convenient and populated methods is taking nutritional supplements like vitamin everyday. According to social currency, we realize ' Automatic Pill Dispenser (APD)' in order to make the storage of pills easy and to help people take pills steadily periodically. First, the APD alerts at the time when the user sets. To prevent polluting pills, if the ultrasonic sensor recognizes user hands, and then after the APD distributes pills through activating the motor. If there are more the APDs, for example, hospitals can manage manpower more efficiently. Furthermore, If it is recorded which and how much pills are distributed automatically, It can be expected that people can take the pills more efficiently and healthfully.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.4
• /
• pp.9-16
• /
• 2019

In this paper, we propose a hydrodynamic scene separation method for wave propagation from video imagery using autoencoder. In the coastal area, image analysis methods such as particle tracking and optical flow with video imagery are usually applied to measure ocean waves owing to some difficulties of direct wave observation using sensors. However, external factors such as ambient light and weather conditions considerably hamper accurate wave analysis in coastal video imagery. The proposed method extracts hydrodynamic scenes by separating only the wave motions through minimizing the effect of ambient light during wave propagation. We have visually confirmed that the separation of hydrodynamic scenes is reasonably well extracted from the ambient light and backgrounds in the two videos datasets acquired from real beach and wave flume experiments. In addition, the latent representation of the original video imagery obtained through the latent representation learning by the variational autoencoder was dominantly determined by ambient light and backgrounds, while the hydrodynamic scenes of wave propagation independently expressed well regardless of the external factors.

• Smart Media Journal
• /
• v.8 no.3
• /
• pp.95-103
• /
• 2019

The global manufacturing industry has reached the limit to growth due to a long-term recession, the rise of labor cost and raw material. As a solution to these difficulties, we promote the 4th Industry Revolution based on ICT and sensor technology. Following this trend, this paper proposes the design of a model using manufacturing data in the protection film process for smart manufacturing innovation. In the protective film process, the manufacturing data of temperature, pressure, humidity, and motion and thermal image are acquired by various sensors for the raw material blending, stirring, extrusion, and inspection processes. While the acquired manufacturing data is stored in mass storage, A.I. platform provides time-series image analysis and its visualization.