• Proceedings of the KSME Conference
• /
• 2001.11a
• /
• pp.791-796
• /
• 2001

Welding using lasers can be mass-produced in high speed. In the laser welding, performing real-time evaluation of the welding quality is very important in enhancing the efficiency of welding. In this study, the plasma and molten metal which are generated during laser welding were measured using the UV sensor and IR sensor. The results of laser welding were classified into five categories such as optimal heat input, little low heat input, low heat input, focus off, and nozzle change. Also, a system was formulated which uses the measured signals with a fuzzy pattern recognition method which is used to perform real-time evaluation of the welding quality and the defects which can occur in laser welding. Weld quality prediction program was developed using previous weld results and statistical program which could show the trend of weld quality and signal was developed.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.458-458
• /
• 2000

Quick evaluations of two in-plane orbit maneuvers using small see of real-time CPS navigation solutions were peformed lot the KOMPSAT-1 spacecraft operation. Real-time GPS navigation solutions of the KOMPSAT-1 were collected during the Korean Ground Station(KGS) pass. Only a few sets of position and velocity data after completion of the thruster firing were used for the quick maneuver evaluations. The results were used for antenna pointing data predictions for the next station contact. Normal orbit maneuver evaluations using large see of playback GPS navigation solutions were also performed and the result were compared with the quick evaluation results.

• Journal of Korean Institute of Industrial Engineers
• /
• v.31 no.2
• /
• pp.127-134
• /
• 2005

Human sensibility is assessed by measuring and analyzing various physiological signals in an objective way, or by analyzing adjectives chosen by the subjects in a subjective way. The present study aims at developing an integrated human sensibility assessment system that measures changes in a person's objective and subjective sensibility in real-time and analyzes them in an integrative way. The present system is composed of a real-time subjective sensibility assessment system, an automatic subjective sensibility assessment system and a real-time physiological signal measurement and analysis system for sensibility assessment, which are separated from one another. It can be utilized individually, or can be combined as a synthetic sensibility assessment system for comprehensive sensibility assessment.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.57 no.2
• /
• pp.109-114
• /
• 2008

In this paper, a dynamic learning controller for robot manipulator is implemented using real-time operating system with capabilities of multitasking, intertask communication and synchronization, event-driven, priority-driven scheduling, real-time clock control, etc. The controller hardware system with VME bus and related devices is developed and applied to implement a dynamic learning control scheme for robot manipulator. Real-time performance of the proposed dynamic learning controller is tested and evaluated for tracking of the desired trajectory and compared with the conventional servo controller.

• Journal of Information Processing Systems
• /
• v.11 no.1
• /
• pp.39-56
• /
• 2015

Continuous multi-interval prediction (CMIP) is used to continuously predict the trend of a data stream based on various intervals simultaneously. The continuous integrated hierarchical temporal memory (CIHTM) network performs well in CMIP. However, it is not suitable for CMIP in real-time mode, especially when the number of prediction intervals is increased. In this paper, we propose a real-time integrated hierarchical temporal memory (RIHTM) network by introducing a new type of node, which is called a Zeta1FirstSpecializedQueueNode (ZFSQNode), for the real-time continuous multi-interval prediction (RCMIP) of data streams. The ZFSQNode is constructed by using a specialized circular queue (sQUEUE) together with the modules of original hierarchical temporal memory (HTM) nodes. By using a simple structure and the easy operation characteristics of the sQUEUE, entire prediction operations are integrated in the ZFSQNode. In particular, we employed only one ZFSQNode in each level of the RIHTM network during the prediction stage to generate different intervals of prediction results. The RIHTM network efficiently reduces the response time. Our performance evaluation showed that the RIHTM was satisfied to continuously predict the trend of data streams with multi-intervals in the real-time mode.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.2
• /
• pp.53-60
• /
• 2023

Recently, the demand and traffic volume for various multimedia contents are rapidly increasing through real-time streaming platforms. In this paper, we predict real-time streaming traffic to improve the quality of service (QoS). Statistical models have been used to predict network traffic. However, since real-time streaming traffic changes dynamically, we used recurrent neural network-based deep learning models rather than a statistical model. Therefore, after the collection and preprocessing for real-time streaming data, we exploit vanilla RNN, LSTM, GRU, Bi-LSTM, and Bi-GRU models to predict real-time streaming traffic. In evaluation, the training time and accuracy of each model are measured and compared.

• The Journal of the Korea Contents Association
• /
• v.13 no.3
• /
• pp.22-31
• /
• 2013

For the case of test equipments requiring data accuracy, real-time is highly required in acceptance test for performance evaluation of developed weapons. For convenience' sake, test equipments are usually developed using Windows. However Windows does not support real-time in itself. Thus, in this paper, so as to reduce development time and expenses, we design and implement an integrated middleware for real-time device drivers using RTiK-MP. Using DLL, we also support user API's for the sake of development convenience without details of the complex RTiK-MP structure. We evaluate the performance of the proposed integrated middleware using the RDTSC command which returns the number of CPU clock ticks. The evaluation results show that it operates correctly within error ranges in the periods of 1ms and 4ms for the cases of TCP/IP and RS-232, respectively.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.1
• /
• pp.42-58
• /
• 2008

Nowadays the installation of Real-time Traffic Signal Control system is gradually spread, in order to solve the traffic problem which become serious. The most important thing are reliability of data collection and functionality of system in Real-time Traffic Signal Control System. But, the evaluation for those introduction system are defective after system constructing. So, many systems are not working properly to those systems's primarily purpose. This study is executed expansion through field test and analysis which check performance and advise of system operation. It has purpose to establish of the maintenance system of Real-time Traffic Signal Control system. As the result of analysis, we could find the several problems in this study. So, we also could guess that the effective maintenance systems of the Real-time Traffic Signal Control system is necessary within few years.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.10
• /
• pp.3885-3892
• /
• 2010

Safety-Critical systems, such as Plant Protection Systems in nuclear power plant, plays a key role that the facilities can be operated without undue risk to the health and safety of public and environment, and those systems shall be designed, fabricated, installed, and tested to quality standards commensurate with the importance of the functions to be performed. Computer-based Instrumentation and Control Systems to perform the safety-critical function have Real Time Operating Systems to control and monitoring the sub-system and executing the application software. The safety-critical Real Time Operating Systems shall be designed, analyzed, tested and evaluated to have capability to maintain a high integrity and quality. However, local nuclear power plants have applied the real time operating systems on safety critical systems through Commercial Grade Item Dedication method, and this is the reason of lack of detailed methodology on assessing the safety of real time operating systems, expecially to the new developed one. This paper presents the methodology and experiences of safety evaluation on safety-critical Real Time Operating Systems based upon design requirements. This paper may useful to develop and evaluate the safety-critical Real Time Operating Systems in other industry to ensure the safety of public and environment.

• Journal of Wetlands Research
• /
• v.14 no.3
• /
• pp.385-397
• /
• 2012

A grid based physically distributed model analyzes rainfall-runoff using physical parameters and grid-typed spatial and hydrological data. This study have developed a real time runoff modelling system using GRM RT(Grid based Rainfall-runoff Model Real Time) which is a real time flow analysis module in GRM, a grid based physically distributed rainfall-runoff model. Weather radar data received in real time are calibrated by using real time AWS from Korea Meteorological Administration(KMA), and they are applied to real time runoff modeling. And the runoff model is calibrated by using observed discharges from a water level gauge in real time. This study have designed and implemented the databases necessary to construct the real time runoff modelling system, and established the process of a real time runoff modelling. And the performances of the developed system have been evaluated. The system have been applied to Nerinheon watershed located in the upstream of Soyanggang Dam and the application results are evaluated.