Optimal Regularization for System Identification from Noisy Input and Output Signals
スポンサーリンク
概要
- 論文の詳細を見る
In identification of a finite impulse response (FIR) model using noise-corrupted input and output data, the least squares type of estimation schemes such as the ordinary least squares (LS), the corrected least squares (CLS) and the total least squares (TLS) methods become often numerically unstable, when the true input signal to the system is strongly correlated. To overcome this ill-conditioned problem, we propose a regularized CLS estimation method by introducing multiple regularization parameters to minimize the mean squares error (MSE) of the regularized CLS estimate of the FIR model. The asymptotic MSE can be evaluated by considering the third and fourth order cross moments of the input and output measurement noises, and an analytical expression of the optimal regularization parameters minimizing the MSE is also clarified. Furthermore, an effective regularization algorithm is given by using the only accessible input-output data without using any true unknown parameters. The effectiveness of the proposed data-based regularization algorithm is demonstrated and compared with the ordinary LS, CLS and TLS estimates through numerical examples.
- 社団法人電子情報通信学会の論文
- 1995-12-25
著者
-
SANO Akira
Department of Analytical Chemistry, Faculty of Pharmaceutical Sciences, Science University of Tokyo
-
Sano A
Keio Univ. Yokohama‐shi Jpn
-
Ohmori Hiromitsu
Department Of Electrical Engineering Keio University
-
Sano Akira
The Faculty Of System Design Engineering Keio University
-
Xin Jingmin
Department Of Electrical Engineering Keio University
-
Sano Akira
Department Of System Design Engineering Keio University
-
Sano Akira
Department Of Electrical Engineering Keio University
-
Sano Akira
Department Of Analytical Chemistry Faculty Of Pharmaceutical Sciences Science University Of Tokyo
関連論文
- Liposome Electrokinetic Chromatography as a Novel Tool for the Separation of Hydrophobic Compounds
- 第17回IFAC世界大会に参加して(国際会議の報告)
- Microarray comparative genomic hybridization analysis of 59 patients with schizophrenia
- Changes in expression of prosaposin in the rat facial nerve nucleus after facial nerve transection
- Positional Candidate Approach for the Gene Responsible for Benign Adult Familial Myoclonic Epilepsy
- Breast Conservation for Huge-sized Locally Advanced Breast Cancer: A Case Report
- A Case of Nodular Pulmonay Amyloidosis
- Systemic Arterial Supply to Normal Basilar Segments of the Left Lower Lobe: Role of Continuous Thin Sliced CT
- Hydrogen Fermentation by Using Heat-Shocked Granular Sludge
- Enhancement in Biodegradability of Excess Sludge by Using a Centrifugal Vibration Mill
- Sequential Analysis of Reducing Oligosaccharides Based on a Chemical Reaction Using 8-Amino-2-naphthalenesulfonic Acid
- A Chemical Approach for Sequential Analysis of Reducing Oligosaccharides
- Determination of L-Ascorbic Acid by a Flow Injection Analysis with Copper(II)-Mediated Electrochemical Detection
- Optical Resolution of Thiol Enantiomers by High-Performance Liquid Chromatography Using Precolumn Fluorescence Derivatization with ο-Phthaladehyde and α-Amino Acids
- Stability Analysis of Exact Model Matching Control for Finite Volterra Series Systems
- Directions-of-Arrival Estimation of Cyclostationary Coherent Signals in Array Processing(Special Section on Digital Signal Processing)
- Robust Adaptive Approach to Semi-active Control of Suspension Systems with MR Damper
- Optimal Regularization for System Identification from Noisy Input and Output Signals
- Adaptive Control Design for Linear Time-Varying System Based on Internal Model Principle
- Blind Identification of Transfer Function Model (Special Section on Digital Signal Processing)
- Positron emission tomography with glucose hypermetabolism of a hypothalamic hamartoma in infantile spasms associated with Pallister-Hall syndrome
- A Recursive Algorithm for Tracking DOA's of Multiple Moving Targets by Using Linear Approximations
- Directions-of-Arrival Tracking of Coherent Cyclostationary Signals in Array Processing(Digital Signal Processing)
- Fluorometric Determination of N-Nitroso-N-methylurea with Nicotinamide and Acetophenone
- Effect of Subarray Size on Direction Estimation of Coherent Cyclostationary Signals Based on Forward-Backward Linear Prediction(Special Section on Digital Signal Processing)
- Identification-Based Predistortion Scheme for High Power Amplifiers
- Chiral Separation of(R, S)-1, 1'-Binaphthyl-2, 2'-diyl Hydrogenphosphate by Capillary Electrophoresis Using Monosaccharides as Chiral Selectors
- Chemiluminescence Detection of Thiols by High-Performance Liquid Chromatography Using o-Phthalaldehyde and N-(4-Aminobutyl)-N-ethylisoluminol as Precolumn Derivatization Reagents
- Remapping and mutation analysis of benign adult familial myoclonic epilepsy in a Japanese pedigree
- Determination of Critical Micelle Concentration of Anionic Surfactants by Capillary Electrophoresis Using 2-Naphthalenemethanol as a Marker for Micelle Formation
- Atypical childhood absence epilepsy with preceding or simultaneous generalized tonic clonic seizures