• Journal of Information Processing Systems
• /
• v.8 no.2
• /
• pp.191-212
• /
• 2012

Since a social network by definition is so diverse, the problem of estimating the preferences of its users is becoming increasingly essential for personalized applications, which range from service recommender systems to the targeted advertising of services. However, unlike traditional estimation problems where the underlying target distribution is stationary; estimating a user's interests typically involves non-stationary distributions. The consequent time varying nature of the distribution to be tracked imposes stringent constraints on the "unlearning" capabilities of the estimator used. Therefore, resorting to strong estimators that converge with a probability of 1 is inefficient since they rely on the assumption that the distribution of the user's preferences is stationary. In this vein, we propose to use a family of stochastic-learning based Weak estimators for learning and tracking a user's time varying interests. Experimental results demonstrate that our proposed paradigm outperforms some of the traditional legacy approaches that represent the state-of-the-art technology.

• Journal of Advanced Marine Engineering and Technology
• /
• v.31 no.5
• /
• pp.599-605
• /
• 2007

This paper presents a method for identifying various systems based on input-output data and a real-coded genetic algorithm(RCGA). The advantages of this technique are, first, it is not dependent on the deterministic or stochastic nature of the systems and, second, the globally optimized models for the original systems can be identified without the need of a differentiable measure function of linearly separable parameters. Under suitable hypotheses, the estimation error is shown to converge in probability to zero. The performance of the proposed algorithm is demonstrated through several simulations.

• Journal of Korean Institute of Industrial Engineers
• /
• v.26 no.4
• /
• pp.392-401
• /
• 2000

In this work, a deadlock avoidance strategy is proposed in order to effectively handle conflicts and deadlocks occurring in zone-control AGV (Automated Guided Vehicle) systems. The basic idea is based on Capacity-designated Directed Graph (CDG) theory that was developed to avoid from deadlocks in manufacturing systems. However, to enforce the effectiveness of detecting impending and restricted deadlocks, AGV routings are explicitly described in Extended Directed Graph (EDG). From EDG, a non-conservative deadlock-avoidance strategy is derived. The superiority of the proposed strategy lies on the applicability to diverse AGV path configurations using zone control. Also, because of its insensibility and robustness, it can be effectively used when the system has randomness and stochastic nature.

• International Journal of Safety
• /
• v.5 no.2
• /
• pp.6-11
• /
• 2006

The time delay in servo control on LonWorks/IP Virtual Device Network (VDN) is highly stochastic in nature. LonWorks/IP VDN induced time delay deteriorates the performance and stability of the real-time distributed control system and hinders an effective preventive and predictive maintenance. Especially in real-time distributed servo applications on the factory floor, timely response is essential for predictive and preventive maintenance. In order to guarantee the stability and performance of the system for effective preventive and predictive maintenance, LonWorks/IP VDN induced time delay needs to be predicted and compensated for. In this paper position control simulation of DC servo motor using Zero Phase Error Tracking Controller (ZPETC) as a feedforward controller, and Internal Model Controllers (IMC) based on Smith predictor with disturbance observer as a feedback controller is performed. The validity of the proposed control scheme is demonstrated by comparing the IMC based on Smith predictor with disturbance observer.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.7
• /
• pp.771-779
• /
• 2004

Unsteady behavior of the early wake in the viscous flow field past an impulsively started semicircular cylinder is studied numerically. In this paper, we propose the hybrid diffusion scheme to simulate dynamic characteristics of wake such as a fishtail-like flapping and an alternate vortex-shedding more accurately. This diffusion scheme based on particle strength exchange is mixed with the stochastic nature of random walk method. Also, the viscous splitting algorithm which calculates convective and diffusion terms successively is applied in order to handle random walk method effectively. Consequently, the early behavior of wake due to the breakdown of symmetrical vortici balance is more practically simulated with the vortex particle method.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2003.03a
• /
• pp.157-164
• /
• 2003

A simulation-based approach that can be used to systematically model the uncertainties of seismic loading and geotechnical property is presented in the context of reliability analysis of slope stability. The uncertainty of seismic loading is studied by generating a large series of hazard-compatible artificial motions, and by using them in subsequent response analyses. The stochastic nature of spatially varying material properties and also the uncertainty arising from insufficient information are treated in the framework of random fields. The simulation-based analyses indicate that in a seismically less active region, a moderate variability in soil properties has a relatively large effect as much as characterization of earthquake hazard on the computed risk of slope failure and excessive slope deformations.

• Journal of the Korea Society for Simulation
• /
• v.10 no.3
• /
• pp.71-82
• /
• 2001

Considering material handling delay which occurs between storage and processing stations, we propose an algorithm to estimate the required storage capacity, i.e., number of aisles and number of openings in vertical and horizontal directions in each aisle, of an automated storage/retrieval(AS/R) system. Due to the random nature of storage and retrieval requests, proportion of single and dual commands is not known in advance. Two design criteria, maximum permissible overflow probability and maximum allowable storage/retrieval(S/R) machine utilization, are used to compute the storage capacity. Most of studies assume that storage capacity of AS/R systems is given, although it is a very important decision variable in the design phase. Therefore, the proposed model can be effectively used in the design phase of new AS/R systems.

• Smart Media Journal
• /
• v.9 no.4
• /
• pp.36-43
• /
• 2020

The Monte Carlo tree search (MCTS) is a popular method for implementing an intelligent game program. It has several hyper-parameters that require an optimization for showing the best performance. Due to the stochastic nature of the MCTS, the hyper-parameter optimization is difficult to solve. This paper uses the self-playing capability of the MCTS-based game program for optimizing the hyper-parameters. It seeks a winner path over the hyper-parameter space while performing the self-play. The top-q longest winners in the winner path compete for the final winner. The experiment using the 15-15-5 game (Omok in Korean name) showed a promising result.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.23 no.5
• /
• pp.605-615
• /
• 1986

The phase-locked loop(PLL) is a communication receiver which operates as a coherent detector by continuously correcting the phase error. In this paper analysis for the Phase-error behavior of analog phase-locked loop (APLL) in the presence of additive white gaussian noise has been done theoretically and experimentally. A close form solution of the first-order loop is obtained and approximate solutions are derived for the second-order loops with RC, leadlag and perfect integrator filters. The perdormance of APLL's and their characteristics are also thoroughly investigated through experiments. In order to analyze the effect of the stochastic nature on nonlinear dynamics characteristics of the second order APLL, the phase error distribution and its variance have been obtained by using the Fokker-Planck equation. Theoretical results agree closely with those of experiment.

• Geomechanics and Engineering
• /
• v.38 no.5
• /
• pp.467-476
• /
• 2024

This study investigates Tunnel Boring Machine (TBM) performance prediction by employing discrete event simulation technique, which is a potential remedy highlighting its stochastic adaptability to the complex nature of TBM tunnelling activities. The new discrete event simulation model using AnyLogic software was developed and validated by comparing its results with actual performance data for Daegok-Sosa railway project that Earth Pressure Balance (EPB) TBM machine was used in Korea. The results showed the successful implementation of predicting TBM performance. However, it necessitates high-quality database establishment including geological formations, machine specifications, and operation settings. Additionally, this paper introduces a novel methodology for daily performance updates during construction, using automated data processing techniques. This approach enables daily updates and predictions for the ongoing projects, offering valuable insights for construction management. Overall, this study underlines the potential of discrete event simulation in predicting TBM performance, its applicability to other tunneling projects, and the importance of continual database expansion for future model enhancements.