• Journal of Information Processing Systems
• /
• 제11권1호
• /
• 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.

• 전자통신동향분석
• /
• 제36권4호
• /
• pp.145-153
• /
• 2021

Data imputation is a crucial issue in data analysis because quality data are highly correlated with the performance of AI models. Particularly, it is difficult to collect quality time-series data for uncertain situations (for example, electricity blackout, delays for network conditions). Thus, it is necessary to research effective methods of time-series data imputation. Many studies on time-series data imputation can be divided into 5 parts, including statistical based, matrix-based, regression-based, deep learning (RNN and GAN) based methodologies. This study reviews and organizes these methodologies. Recently, deep learning-based imputation methods are developed and show excellent performance. However, it is associated to some computational problems that make it difficult to use in real-time system. Thus, the direction of future work is to develop low computational but high-performance imputation methods for application in the real field.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.304-309
• /
• 2015

On construction sites, it is important to monitor the performance of construction equipment and workers to achieve successful construction project management; especially, vision-based detection methods have advantages for the real-time site data collection for safety and productivity analyses. Although many researchers developed vision-based detection methods with acceptable performance, there are still limitations to be addressed: 1) sensitiveness to the shape and appearance changes of moving objects in difference working postures, and 2) high computation time. To deal with the limitations, this paper proposes a detection algorithm of construction equipment based on Integral Channel Features. For validation, 16,850 frames of video streams were recorded and analyzed. The results showed that the proposed method worked in high performance in terms of accuracy and processing time. In conclusion, the developed method can help to understand useful site information including working pattern, working time and input manpower analyses.

• 한국지진공학회논문집
• /
• 제22권4호
• /
• pp.253-259
• /
• 2018

Structure behaviors resulting from an earthquake are experimentally simulated mainly through a shaking table test. As for large-scale structures, however, size effects over a miniature may make it difficult to assess actual behaviors properly. To address this problem, research on the hybrid simulation is being conducted actively. This method is to implement numerical analysis on framework members that affect the general behavior of the structure dominantly through an actual scale experiment and on the rest parts by applying the substructuring technique. However, existing studies on hybrid simulation focus mainly on Slow experimental methods, which are disadvantageous in that it is unable to assess behaviors close to the actual level if material properties change depending on the speed or the influence of inertial force is significant. The present study aims to establish a Real-time hybrid simulation system capable of excitation based on the actual time history and to verify its performance and applicability. The hybrid simulation system built up in this study utilizes the ATS Compensator system, CR integrator, etc. in order to make the target displacement the same with the measured displacement on the basis of MATLAB/Simulink. The target structure was a 2-span bridge and an RC pier to support it was produced as an experimental model in order for the shaking table test and Slow and Real-time hybrid simulations. Behaviors that result from the earthquake of El Centro were examined, and the results were analyzed comparatively. In comparison with the results of the shaking table test, the Real-time hybrid simulation produced more similar maximum displacement and vibration behaviors than the Slow hybrid simulation. Hence, it is thought that the Real-time hybrid simulation proposed in this study can be utilized usefully in seismic capacity assessment of structural systems such as RC pier that are highly non-linear and time-dependent.

• 전자공학회논문지A
• /
• 제33A권6호
• /
• pp.23-32
• /
• 1996

This paper proposes a new buffer management scheme to service delay-sensitive traffic and loss-sensitive traffic fairly in ATM networks. The proposed scheme uses tow buffers for delay-sensitive traffic and loss-sensitive traffic. To satisfy the average delay time of delay-sensitive traffic, cells in real-time buffer are served first. When congestion occurs in nonreal-time buffer, low loss priority cell in real-time buffer can be pushed out by high loss priority cell in nonreal-time buffer can be transferred to real-time buffer considering threshold value in real-time buffer. Using computer simulation, the existing methods and proposed scheme are compared and analyzed with respect to cell loss rate and average delay time. Simulation results show that the proposed scheme have superior performance to conventional schemes.

• 정보처리학회논문지A
• /
• 제12A권5호
• /
• pp.427-432
• /
• 2005

웹 클러스터 시스템에서 사용자들의 접속 요구를 효율적으로 real 서버에 분산시키기 위하여 기존의 부하분산 알고리즘들과 현재 많이 사용중인 WLC(Weighted Least Connection) 알고리즘에 대하여 연구하였다. 이 부하분산 알고리즘들은 서버들의 부정확한 부하상태 파악과 파악 시점에 문제가 있어 서버들 간에 부하 불균형이 발생함으로써 효율성이 저하된다. 본 연구에서는 사용자의 접속 요청 시 broadcasting RPC(Remote Procedure Call)를 이용하여 서버들의 다양한 부하상태를 실시간으로 파악하여 부하를 분산하는 알고리즘을 제안하고, prototype을 구현하여 성능을 실험하였다. 실험 결과, real 서버 간 부하 불균형 현상이 기존 방법에 비하여 크게 향상되었고, 응답시간이 단축되는 효과로 웹 클러스터 시스템의 성능이 향상되었다.

• 인포메이션 디스플레이
• /
• 제18권3호
• /
• pp.3-12
• /
• 2017

In the recent years, significant advances have been made in the development of small form-factor, low power, and low cost 3D-sensing devices based on depth-imaging technologies with real-time performance. This has led to the advent of devices and machines that are able to sense and understand the world, navigate in the environment, and interact naturally with their human users. Human-computer interactions based on touch sensing and speech recognition have already become mainstream, and the rapid developments in 3D sensing is paving the path towards the next level of machine intelligence and interactions. This paper discusses the recent developments in real-time 3D sensing technologies and their emerging system application.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.1324-1327
• /
• 1996

This paper presents an open architecture controller (OAC) for machining systems and describes the OAC testbed at Seoul National University. Because our OAC is designed for fully open systems, it does not depend on any specific hardware or software components. This openness includes software reusability which enables integration of a wide range of monitoring and control features. In addition to openness, our OAC system provides guaranteed real-time performance, an important requirement for advanced manufacturing.

• 디지털콘텐츠학회 논문지
• /
• 제6권3호
• /
• pp.189-193
• /
• 2005

최근 한국 대학은 급격한 구조조정이 이루어지고 있다. 한국 정부는 모든 4년제 대학교와 2년제 대학에 대해 대학평가를 실시하고 있다. 본 연구에서는 현재의 대학평가지수가 대학의 핵심성과지표(KPI: Key Performance Index) 로서의 의미를 갖는다고 보고 속도의 관점에서 대학평가지수를 분석하여, 대학 역시 의사결정의 속도가 중요함을 보이고 BI(Business Intelligence)시스템과 접목하였다.

• 대한전자공학회논문지
• /
• 제25권2호
• /
• pp.119-124
• /
• 1988

Real-time adaptive lattice predictor was implemented on the TMS32020 DSP chip for digital signal processing. The implemented system was composed of Input-Output units and centrla processing-control unit and its supporting assembly soft ware. The performance of hardware realization was verified by comparing input signal and one-step prediction signal which are calcualted by the real-time adaptive lattice predictor. As a result, for 4 stage lattice structure, the maximum running frequency was obtained as 6.41 KHz in this experiment.