• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.234-237
• /
• 2005

강화학습을 위한 많은 방법 중 정책 반복을 이용한 actor-critic 학습 방법이 많은 적용 사례를 통해서 그 가능성을 인정받고 있다. Actor-critic 학습 방법은 제어입력 선택 전략을 위한 actor 학습과 가치 함수 근사를 위한 critic 학습이 필요하다. 본 논문은 critic의 학습을 위해 빠른 수렴성을 보장하는 RLS(recursive least square)를 사용하고, actor의 학습을 위해 정책의 기울기(policy gradient)를 이용하는 새로운 알고리즘을 제안하였다. 그리고 이를 실험적으로 확인하여 제안한 논문의 성능을 확인해 보았다.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.2
• /
• pp.248-254
• /
• 2018

In this paper, a Monte Carlo-based Recursive Least Square(MC-RLS) method is presented to directly identify the inverse model of the dynamical system. Although a RLS method has been used for the identification based on the deterministic data in the closed loop controlled form, it would be better for RLS to identify the model with random data. In addition, the inverse model obtained by inverting the identified forward model may not work properly. Therefore, MC-RLS can be used for the inverse model identification without proceeding a numerical inversion of an identified forward model. The performance of the proposed method is verified through experimental studies on a control moment gyroscope.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.12
• /
• pp.978-982
• /
• 2009

This paper proposes a potential-based reinforcement learning, called "RLs-CBDT", which combines multiple RL agents and case-base decision theory designed for decision making in uncertain environment as an expert knowledge in RL. We empirically show that RLs-CBDT converges to an optimal policy faster than pre-existing RL algorithms through a Tetris experiment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.5A
• /
• pp.521-528
• /
• 2011

In sensor network environment, it is very important to localize sensor nodes. In order to know the position of nodes without GPS signals, the anchor robot approach is representatively used. Therefore, in this paper, we propose 4-Robot Localization Scheme (4RLS) that uses four mobile robots to efficiently localize sensor nodes for the fast time. Then, we show the improved performance of 4RLS in comparison with previously used three robot scheme through the real implementation and analysis.

• Proceedings of the KIEE Conference
• /
• 1999.11c
• /
• pp.488-490
• /
• 1999

This paper describes the design of self-tuning speed controller for DC motor drive system using RLS(Recursive Least Squares) algorithm and Pole-Placement method. The model parameters, related to inertia and damping coefficient of motor, are estimated on-line by using RLS estimation algorithm. And a control signal is calculated by using pole placement method. Simulation and experimental results show that the proposed controller possesses excellent adaptation capability than a conventional PI/IP controller under parameter change.

• Proceedings of the KIEE Conference
• /
• 2006.11a
• /
• pp.279-281
• /
• 2006

A Voltage Instability Predictor(VIP) estimates the proximity of a power system to voltage collapse in real time. Voltage Instability Index(Z-index) from VIP algorithm is estimated using LS(Least Square) method. But this method has oscillations and noise of result due to the system's changing conditions. To suppress oscillations, a larger data window needs to be used. In this paper. I propose the new other method which improves that weakness. It uses RLS(Recursive Least Square) to estimate voltage instability index without a large moving data window so this method is suitable for on-line monitor and control in real time. In order to verify effectiveness of the algorithm using RLS method, the method is tested on HydroQuebec system in real time digital simulator(HYPERSIM).

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.537-538
• /
• 2016

본 논문은 사무용 건물의 효율적인 에너지 관리를 위하여 실제 사무용 건물의 전력 사용량 빅 데이터를 이용하여 RLS 알고리즘을 활용한 사용량 예측 모델을 설계하였다. 예측모델을 통해 도출된 예측치와 실측 데이터 사이의 오차율을 계산하고, MA알고리즘을 사용한 예측값과의 비교를 통해 제안하는 변형된 RLS 알고리즘을 이용한 에너지 사용량 예측 방법론의 타당성과 우수성을 검증하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.12A
• /
• pp.1836-1842
• /
• 2000

이 논문은 레일레이 감쇄 채널 환경에서 IMT-2000 파일럿 심볼 구조의 W-CDMA 시스템 역방향 링크의 채널 추정에 관한 LMS 적용형 알고리즘 성능을 WMSA(Weighted Multi-Slot Averaging)(K=1,2,3), 일정 추정이득 (Constant estimation gain) 및 RLS 알고리즘 성능과 비교 분석하였다. 이 논문의 모형은 IMT-2000 3GPP 규격의 W-CDMA 채널 구조, 변조 및 파일럿 패턴을 이용하였다. 파일럿 심볼 위치의 채널추정은 LMS 알고리즘을 이용하고 데이터 심볼 위치의 채널보상은 선형 보간으로 수행하였다. 저속 도플러 주파수에서는 WMSA(K=1,2,3) 성능이 일정 추정이득, RLS 및 LMS 적응형 알고리즘 성능보다 우수하며, WMSA(K=1) 성능의 경우 일정 추정이득, RLS 및 LMS 적응형 알고리듬 성능과는 큰 차이가 없다. 그리고 LMS 알고리즘 성능은 WMSA(K=1) 성능과 매우 비슷한 결과를 얻었다. 그러나 도플러 주파수가 고속화될수록 LMS 알고리즘의 성능이 WMSA(K=1), 일정 추정이득 및 RLS 알고리즘 성능보다 우수함을 확인하였다.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.25 no.4
• /
• pp.641-649
• /
• 2011

This study was purposed to evaluate the effects of root of Liriope spicata (RLS) on LPS-induced COPD (chronic obstructive pulmonary disease) model. The extract of RLS was treated to A549 cells and LPS-induced COPD mice model. Then, various parameters such as cell-based cyto-protective activity and histopathological finding were analyzed. RLS showed a protective effect on LPS-induced cytotoxicity in A549 cells. This effect was correlated with analysis for caspase 3 levels, protein level of cyclin B1, Cdc2, and phospho-Erk1/2, and gene expression of TNF-${\alpha}$ and IL-$1{\beta}$ in A549 cells. RLS treatment also revealed the protective effect on LPS-induced lung injury in COPD mice model. This effect was evidenced via histopathological finding including immunofluence stains against caspase 3, and protein level of cyclin B1, Cdc2, and Erk1/2 in lung tissue. These data suggest that RLS has a pharmaceutical properties on lung injury. This study would provide an scientific evidence for the efficacy of RLS for clinical application to patients with COPD.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.47 no.6
• /
• pp.1-9
• /
• 2010

In this paper, we propose a hi-speed/low-power Extended QRD-RLS(QR-Decomposition Recursive Least Squares) equalizer with systolic array structure. In the conventional systolic array structure, vector mode CORDIC on the boundary cell calculates angle of input vector, and the rotation mode CORDIC on the internal cell rotates vector. But, in the proposed structure, it is shown that implementation complexity can be reduced using the rotation direction of vector mode CORDIC and rotation mode CORDIC. Furthermore, calculation time can be reduced by 1/2 since vector mode and rotation mode CORDIC operate at the same time. Through HDL coding and chip implementation, it is shown that implementation area is reduced by 23.8% compared with one of conventional structure.