• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.227-241
• /
• 2021

Object detection techniques based on deep learning such as YOLO have high detection performance and precision in a single channel video stream. In order to expand to multiple channel object detection in real-time, however, high-performance hardware is required. In this paper, we propose a novel back-end server framework, a real-time AI vision platform (RAVIP), which can extend the object detection function from single channel to simultaneous multi-channels, which can work well even in low-end server hardware. RAVIP assembles appropriate component modules from the RODEM (real-time object detection module) Base to create per-channel instances for each channel, enabling efficient parallelization of object detection instances on limited hardware resources through continuous monitoring with respect to resource utilization. Through practical experiments, RAVIP shows that it is possible to optimize CPU, GPU, and memory utilization while performing object detection service in a multi-channel situation. In addition, it has been proven that RAVIP can provide object detection services with 25 FPS for all 16 channels at the same time.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.8 s.197
• /
• pp.50-57
• /
• 2007

In this paper, two types of novel planar Translational Parallel Manipulators (TPMs) by using parallelogram mechanism are conceived. One is made up of two Pa-P (Parallelogram-Prismatic) legs connecting the base to the moving platform. The other consists of two P-Pa legs, which is the kinematic inversion of the former. Since connecting links in a parallelogram mechanism are subject to only tensile/compressive load and all the heavy actuators are mounted at the base, the proposed manipulators can be applied for planar positioning/assembly tasks requiring high stiffness and high speed. The position, velocity, and statics are analyzed, and the design methodology using prescribed workspace and velocity transmission capability is presented. Finally, two types of prototype manipulators have been developed.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.1075-1087
• /
• 2020

Aviation ICT technology is a convergence technology between aviation and electronics, and has a wide variety of applications, including navigation and education. Among them, in the field of aerial pilot training, there are many problems such as the possibility of accidents during training and the lack of coping skills for various situations. This raises the need for a simulated pilot training system similar to actual training. In this paper, pilot training data were collected in pilot training system using VR/AR to increase immersion in flight training, and Customized Pilot Training Platform with Collaborative Deep Learning in VR/AR Environment that can recommend effective training courses to pilots is proposed. To verify the accuracy of the recommendation, the performance of the proposed collaborative deep learning algorithm with the existing recommendation algorithm was evaluated, and the flight test score was measured based on the pilot's training data base, and the deviations of each result were compared. The proposed service platform can expect more reliable recommendation results than previous studies, and the user survey for verification showed high satisfaction.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.5
• /
• pp.825-836
• /
• 2019

The drone-type base station will be an optimal platform as a way of information sharing for efficient operation of the military force due to their high network flexibility. It is expected that the characteristics of the drone-type base station which would freely adjust the altitude can be used to offset the propagation attenuation characteristics of the millimeter-wave frequency band by securing the stable Line of Sight. In this paper, we proposed a framework for evaluation drone-type base station that can be utilized as a future military communication network by performing modeling for performance analysis that can reflect various factors.

• Advances in nano research
• /
• v.16 no.1
• /
• pp.81-90
• /
• 2024

In the oil and gas industry, composite materials should exhibit high flexibility and strength for offshore structures. Therefore, weak points in the composites should be improved, such as brittleness, moisture penetration, and diffusion of detrimental ions into nanometric pores. This study aimed to increase the strength, flexibility, and plugging of nanopores using single-layer graphene oxide (SGO) nanosheets. Therefore, SGO is added to unsaturated polyester resin at concentrations of 0.015 and 0.15 % with Normal Methyl Pyrrolidone (NMP) as a solvent for the formation of Nanographene Oxide Reinforced Polymer (NGORP). The mechanical properties of the prepared samples were tested using tensile testing (ASTM-D 638). It has been shown that incorporating SGO, approximately 0.015%, into the base resin resulted in enhanced properties such as rupture resistance forces increased by 745.61 N, applied stress tolerances increased by 4.1 MPa, longitude increased to 1.58 mm, elongation increased by about 2.38%, and rupture energy increased by about 204.51 J. Despite the decrease in tensile force strength properties in the manufactured nanocomposite with 0.15% SGO, it has exclusive flexibility properties such as a high required energy level for rupture of 5,576 times and a formability of 40% more than the base sample. It would be best to use NGORP manufactured from 0.015% nanosheets with exclusive properties rather than base samples for constructing parts and equipment, such as rebars, composite sheets, and transmission pipes, on offshore platforms.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2235-2239
• /
• 2003

The aim of this research is to study and develop enabling technologies for home healthcare device with ubiquitous network. The motivation of this paper is to enable healthcare in home, to development the device for smart home health care. To achieve the aim, we must develop the prototype platform based on home gateways, distributed context user interface based on UPnP and support for information sharing with high speed power line communication and mobile infra-structures. And IPv6 is the base technology of this platform. In this paper, we concern that physical health, mental health and medical emergencies is all of home healthcare. With the smart device, we evaluate the connectivity, automatic information extraction and private data exchange and event driven message. The result of this paper is demonstration of smart device for ubiquitous communication in a healthcare application such as patient monitoring device and several information services. In conclusion, home healthcare will support more healthy and easy living for a human.

• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.2
• /
• pp.25-37
• /
• 2015

In recent years, the advance on the high-end converging technology has improved to the changes on digital signage technology in many ways. Digital signage has to be designed to give information through systemed structure among the constituent for developing the information delivery responding to the environmental conversion, not feeding user information. Therefore, this paper proposes a smart contents platform which supplies various from of digital signage contents. In the digital signage circumstance, the smart contents platform is a way for an effective information transmission, game and the advertising interface by recognizing user interaction and the environmental information. This platform is composed of base hardware, middleware and middle device. Each component module is managed by the smart contents platform. Furthermore, it serves various live contents experiences via gathering and analyzing user and environmental information with linking various sensors and devices. It is a new way of information delivery which serves contents producing and providing circumstances in parallel.

• Journal of Korea Multimedia Society
• /
• v.11 no.11
• /
• pp.1525-1535
• /
• 2008

High Altitude Platform (HAP) based networks deploy network infrastructures of Mobile Base Station (MBS) in a form of Unmanned Aerial Vehicle (UAV) at stratosphere in order to build network configuration. The ultimate goal of HAP based network is a wireless network service for wide area by deploying multiple MBS for such area. In this paper we assume multiple UAVs over designated area and solve the MBS placement and coverage problem by clustering the mobile ground nodes. For this study we assumed area around Cheju island and nearby naval area where multiple mobile and fixed nodes are deployed and requires HAP based networking service. By simulation, visual results of stratospheric MBS placement have been presented. These results include clustering, MBS placement and coverage as well as dynamic reclustering according to the movement of mobile ground nodes.

• Smart Structures and Systems
• /
• v.32 no.2
• /
• pp.83-99
• /
• 2023

The temperature prediction approaches of three important locations in an operational longitudinal slab track-bridge structure by using three typical neural network methods based on the field measuring platform of four meteorological factors and internal temperature. The measurement experiment of four meteorological factors (e.g., ambient temperature, solar radiation, wind speed, and humidity) temperature in the three locations of the longitudinal slab and base plate of three important locations (e.g., mid-span, beam end, and Wide-Narrow Joint) were conducted, and then their characteristics were analyzed, respectively. Furthermore, temperature prediction effects of three locations under five various meteorological conditions are tested by using three neural network methods, respectively, including the Artificial Neural Network (ANN), the Long Short-Term Memory (LSTM), and the Convolutional Neural Network (CNN). More importantly, the predicted effects of solar radiation in four meteorological factors could be identified with three indicators (e.g., Root Means Square Error, Mean Absolute Error, Correlation Coefficient of R2). In addition, the LSTM method shows the best performance, while the CNN method has the best prediction effect by only considering a single meteorological factor.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.2
• /
• pp.146-158
• /
• 1996

This paper develops a robot arm for propeller blade grinding. The grinding work requires a high stiffness robot arm to reduce deformation and vibration which are generated during machining operation. Conventional articulated robots have serial connecting links from the base to the gripper. Thus, they have very weak structure to the stiffness for grinding operation. Stewart Platform is a typical parallel robotic mechanism with very high stiffness but it has small work space and large installation space. This research proposes a new grinding robot arm by combining parallel mechanism with serial mechanism. Therefore, the robot has large range of work space as well as high stiffness. This paper introduces the automatic system for propeller grinding utilizing the robot and the design of proposed robot arm.