A hybrid nonlinear predictor: Analysis of learning process and predictability for noisy time series
スポンサーリンク
概要
- 論文の詳細を見る
A nonlinear time series predictor was proposed, in which a nonlinear sub-predictor (NSP) and a linear subpredictor (LSP) are combined in a cascade form. This model is called hybrid predictor here. The nonlinearity analysis method of the input time series was also proposed to estimate the network size. We have considered the nonlinear prediction problem as a pattern mapping one. A multi-layer neural network, which consists of sigmoidal hidden neurons and a single linear output neuron, has been employed as a nonlinear sub-predictor. Since the NSP includes nonlinear functions, it can predict the nonlinearity of the input time series. However, the prediction is not complete in some cases. Therefore, the NSP prediction error is further compensated for by employing a linear sub-predictor after the NSP. In this paper, the prediction mechanism and a role of the NSP and the LSP are theoretically and experimentally analyzed. The role of the NSP is to predict the nonlinear and some part of the linear property of the time series. The LSP works to predict the NSP prediction error. Furthermore, predictability of the hybrid predictor for noisy time series is investigated. The sigmoidal functions used in the NSP can suppress the noise effects by using their saturation regions. Computer simulations, using several kinds of nonlinear time series and other conventional predictor models, are demonstrated. The theoretical analysis of the predictor mechanism is confirmed through these simulations. Furthermore, predictability is improved by slightly expanding or shifting the input potential of the hidden neurons toward the saturation regions in the learning process.
- 一般社団法人電子情報通信学会の論文
- 1999-08-25
著者
-
Khalaf Ashraf
Graduate School Of Natural Science And Technology Kanazawa University
-
Nakayama Kenji
Department Of Cardiothoracic Surgery Niigata Prefectural Shibata Hospital
-
Nakayama Kenji
Department Of Electrical And Computer Engineering Faculty Of Engineering Kanazawa University
関連論文
- Clinicopathological study of pleomorphic xanthoastrocytoma : Correlation between histological features and prognosis
- Contralateral Development of Acute Subdural Hematoma Following Surgery for Chronic Subdural Hematoma : Case Report
- Change of Patient Position Using a Transportation Board During Lumboperitoneal Shunting : Technical Note
- Modified Draping to Avoid Fluid Leakage in Cranial Surgery : Technical Note
- Video-Assisted Thoracic Surgery for Thorascopic Resection of Giant Bulla
- A-2-13 Comparison of Back-Propagation, Hybrid Learning and Support Vector Machine based on Generalization
- Video-assisted transaortic left ventricular thrombectomy and coronary artery bypass grafting
- Nonlinear resonance effects in a linear Paul trap
- Anchoring of Methylmethacrylate Filler to the Calvarium : Technical Note
- Inclined Foot Switches for Surgical Microscopes : A Comfortable Design for Seated Surgeons : Technical Note
- The tumor of the third ventricle
- Multi-frequency signal classification by multilayer neural networks and linear filter methods
- A cascade form predictor of neural and FIR filters and its minimum size estimation based on nonlinearity analysis of time series
- Depth-Adjustable Fixation of External Ventricular Drains to Counteract Obstruction in Tight Ventricles : Technical Note
- Determination of Transverse Distributions of Ion Plasmas Confined in a Linear Paul Trap by Imaging Diagnostics
- A hybrid nonlinear predictor: Analysis of learning process and predictability for noisy time series
- Hanging Foot Switch for Bipolar Forceps: A Device for Surgeons Operating in the Standing Position:—Technical Note—
- Decompressive hemicraniectomy for acute subdural hematoma.
- RADIOLOGICAL FEATURES OF LIPOMA OF THE CORPUS CALLOSUM
- CT FINDINGS IN AN ALOBAR HOLOPROSENCEPHALY ASSOCIATED WITH DANDY-WALKER'S CYST
- Hanging Foot Switch for Bipolar Forceps : A Device for Surgeons Operating in the Standing Position : Technical Note