scholarly journals Online Prediction of Ship Coupled Heave-Pitch Motions in Irregular Waves Based on a Coarse-and-Fine Tuning Fixed-Grid Wavelet Network

2021 ◽  
Vol 9 (9) ◽  
pp. 989
Author(s):  
Baigang Huang ◽  
Jianjun Jiang ◽  
Zaojian Zou
Keyword(s):  
Modeling Method ◽  
Fine Tuning ◽  
Irregular Waves ◽  
Wavelet Network ◽  
Simulation Data ◽  
Wavelet Networks ◽  
Fixed Grid ◽  
Online Modeling ◽  
Online Prediction ◽  
Tuning Process

A method based on a coarse- and fine-tuning fixed-grid wavelet networks is presented for online prediction of the coupled heave-pitch motions of a ship in irregular waves. The online modeling method contains two processes, i.e., coarse tuning and fine tuning. The coarse tuning is used to select the important wavelet terms, while the fine tuning is only used to compute the related coefficients of the selected wavelet terms. The Givens transformation algorithm is applied to realize the fine-tuning process. Due to the continuous fine-tuning process, the computational efficiency is improved significantly. Both simulation data and experimental data are used to verify the modeling method. The prediction results illustrate that the method has the ability to online predict the coupled heave-pitch motions of a ship in irregular waves.

PYRAMIDAL HYBRID APPROACH: WAVELET NETWORK WITH OLS ALGORITHM-BASED IMAGE CLASSIFICATION

2011 ◽  
Vol 09 (01) ◽  
pp. 111-130 ◽  
Author(s):  
OLFA JEMAI ◽  
MOURAD ZAIED ◽  
CHOKRI BEN AMAR ◽  
MOHAMED ADEL ALIMI
Keyword(s):  
Least Squares ◽  
Image Classification ◽  
Network Architecture ◽  
Hybrid Approach ◽  
Learning Ability ◽  
Wavelet Network ◽  
Wavelet Networks ◽  
Orthogonal Least Squares ◽  
Colour Image ◽  
Beta Wavelet

Taking advantage of both the scaling property of wavelets and the high learning ability of neural networks, wavelet networks have recently emerged as a powerful tool in many applications in the field of signal processing such as data compression, function approximation as well as image recognition and classification. A novel wavelet network-based method for image classification is presented in this paper. The method combines the Orthogonal Least Squares algorithm (OLS) with the Pyramidal Beta Wavelet Network architecture (PBWN). First, the structure of the Pyramidal Beta Wavelet Network is proposed and the OLS method is used to design it by presetting the widths of the hidden units in PBWN. Then, to enhance the performance of the obtained PBWN, a novel learning algorithm based on orthogonal least squares and frames theory is proposed, in which we use OLS to select the hidden nodes. In the simulation part, the proposed method is employed to classify colour images. Comparisons with some typical wavelet networks are presented and discussed. Simulations also show that the PBWN-orthogonal least squares (PBWN-OLS) algorithm, which combines PBWN with the OLS algorithm, results in better performance for colour image classification.

Active control of flexible one-link manipulators using wavelet networks

Robotica ◽  
2013 ◽  
Vol 31 (8) ◽  
pp. 1275-1283 ◽  
Author(s):  
V. I. Gervini ◽  
E. M. Hemerly ◽  
S. C. P. Gomes
Keyword(s):  
Dead Zone ◽  
Flexible Manipulator ◽  
Friction Compensation ◽  
Control Law ◽  
Wavelet Network ◽  
Stick Slip ◽  
Control Laws ◽  
Operational Conditions ◽  
Structure Control ◽  
Wavelet Networks

SUMMARYThe design of control laws for flexible manipulators is known to be a challenging problem, when using a conventional actuator, i.e., a motor with gear. This is due to the friction of the nonlinear actuator, which causes torque dead zone and stick-slip behavior, thereby hampering the good performance of the control system. The torque needed to attenuate the vibrations, although calculated by the control law, is consumed by the friction inside the actuator, rendering it ineffective to the flexible structure control. Nonlinear friction varies with different operational conditions of the actuator and a friction compensation mechanism based on these models cannot always keep a good performance. This study proposes a new control strategy using wavelet network to friction compensation. Experimental results obtained with a flexible manipulator attest to the good performance of the proposed control law.

scholarly journals Fixed grid wavelet network segmentation on diffuse optical tomography image to detect sarcoma

2018 ◽  
Vol 16 (2) ◽  
Author(s):  
K. Uma Maheswari ◽  
S. Sathiyamoorthy
Keyword(s):  
Image Segmentation ◽  
Mean Square Error ◽  
Optical Tomography ◽  
Diffuse Optical Tomography ◽  
Optical Image ◽  
Mean Square ◽  
Wavelet Network ◽  
Fixed Grid ◽  
Image Metrics ◽  
Tumor Region

Objective: To detect and explore the boundary of the sarcoma in Diffuse Optical Tomography (DOT) images, we need to extract the scattering and absorption property of the tissue at the cellular level. The DOT images suffer with lower optical resolution; therefore to improve the resolution in non-invasive imaging technique we apply Fixed Grid Wavelet Network (FGWN) image segmentation. Methods: We have subjected the reconstructed optical image to Vignette Correction to enhance the corners so that it traces the smooth boundary of tumor region. Fixed Grid Wavelet Network segmentation applied to reduce the training with the significant ortho-normal property. R, G and B values of optical image were considered as network inputs which lead to the formation of Wavelet network. Effective wavelet selection was based on Orthogonal Least Squares Algorithm and the network weights were calculated to optimize the network structure. The Mexican hat wavelet chosen facilitates the diffusion operator for image restoration, hence well-suited for Diffuse Optical Tomography (DOT) images.Results: Analysis made on data base of 30 DOT images and the 6 criteria results was evaluated. The boundary of the tumor region was traced on grayscale and the following Image Metrics were measured namely Mean Square Error, Root Mean Square Error, Peak Signal to Noise Ratio, Pearson Correlation Coefficient and Mean absolute error. The Receiver Operating Characteristics (ROC) was estimated at 99.527%, 88.73% and 93.8% with respect to sensitivity, specificity and overall accuracy. Conclusions: FGWN was compared with genetic algorithm and graph cut segmentation based on image metrics which exhibited 5.2% improvement and it was evaluated such that FGWN based image segmentation was superior to other methodologies.

scholarly journals Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation

2020 ◽  
Vol 34 (05) ◽  
pp. 7839-7846
Author(s):  
Junliang Guo ◽  
Xu Tan ◽  
Linli Xu ◽  
Tao Qin ◽  
Enhong Chen ◽  
...  
Keyword(s):  
Machine Translation ◽  
Fine Tuning ◽  
Inference Process ◽  
Neural Machine Translation ◽  
Training Strategy ◽  
Speed Up ◽  
Good Improvement ◽  
Tuning Process ◽  
Translation Accuracy ◽  
The Cost

Non-autoregressive translation (NAT) models remove the dependence on previous target tokens and generate all target tokens in parallel, resulting in significant inference speedup but at the cost of inferior translation accuracy compared to autoregressive translation (AT) models. Considering that AT models have higher accuracy and are easier to train than NAT models, and both of them share the same model configurations, a natural idea to improve the accuracy of NAT models is to transfer a well-trained AT model to an NAT model through fine-tuning. However, since AT and NAT models differ greatly in training strategy, straightforward fine-tuning does not work well. In this work, we introduce curriculum learning into fine-tuning for NAT. Specifically, we design a curriculum in the fine-tuning process to progressively switch the training from autoregressive generation to non-autoregressive generation. Experiments on four benchmark translation datasets show that the proposed method achieves good improvement (more than 1 BLEU score) over previous NAT baselines in terms of translation accuracy, and greatly speed up (more than 10 times) the inference process over AT baselines.

scholarly journals Improving the Performance of Metaheuristics: An Approach Combining Response Surface Methodology and Racing Algorithms

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
Eduardo Batista de Moraes Barbosa ◽  
Edson Luiz França Senne ◽  
Messias Borges Silva
Keyword(s):  
Optimization Problems ◽  
Great Influence ◽  
Solution Process ◽  
Fine Tuning ◽  
Quality Of Results ◽  
Process Understanding ◽  
Tuning Process ◽  
Research Challenge ◽  
Best Fit

The setup of heuristics and metaheuristics, that is, the fine-tuning of their parameters, exercises a great influence in both the solution process, and in the quality of results of optimization problems. The search for the best fit of these algorithms is an important task and a major research challenge in the field of metaheuristics. The fine-tuning process requires a robust statistical approach, in order to aid in the process understanding and also in the effective settings, as well as an efficient algorithm which can summarize the search process. This paper aims to present an approach combining design of experiments (DOE) techniques and racing algorithms to improve the performance of different algorithms to solve classical optimization problems. The results comparison considering the default metaheuristics and ones using the settings suggested by the fine-tuning procedure will be presented. Broadly, the statistical results suggest that the fine-tuning process improves the quality of solutions for different instances of the studied problems. Therefore, by means of this study it can be concluded that the use of DOE techniques combined with racing algorithms may be a promising and powerful tool to assist in the investigation, and in the fine-tuning of different algorithms. However, additional studies must be conducted to verify the effectiveness of the proposed methodology.

scholarly journals Adaptive Prediction of Stock Exchange Indices by State Space Wavelet Networks

2009 ◽  
Vol 19 (2) ◽  
pp. 337-348 ◽  
Author(s):  
Mietek Brdyś ◽  
Adam Borowa ◽  
Piotr Idźkowiak ◽  
Marcin Brdyś
Keyword(s):  
State Space ◽  
Network Model ◽  
Stock Exchange ◽  
Real Data ◽  
Economic Indicators ◽  
Wavelet Network ◽  
Wavelet Networks ◽  
Adaptive Prediction ◽  
Wide Range ◽  
Warsaw Stock Exchange

Adaptive Prediction of Stock Exchange Indices by State Space Wavelet NetworksThe paper considers the forecasting of the Warsaw Stock Exchange price index WIG20 by applying a state space wavelet network model of the index price. The approach can be applied to the development of tools for predicting changes of other economic indicators, especially stock exchange indices. The paper presents a general state space wavelet network model and the underlying principles. The model is applied to produce one session ahead and five sessions ahead adaptive predictors of the WIG20 index prices. The predictors are validated based on real data records to produce promising results. The state space wavelet network model may also be used as a forecasting tool for a wide range of economic and non-economic indicators, such as goods and row materials prices, electricity/fuel consumption or currency exchange rates.

Dynamic Modeling of Nonlinear Systems Using Wavelet Networks

2008 ◽  
Vol 20 (1) ◽  
pp. 178-187 ◽  
Author(s):  
Wissam Hassouneh ◽  
◽  
Rached Dhaouadi ◽  
Yousef Al-Assaf
Keyword(s):  
Nonlinear Systems ◽  
Dynamic Modeling ◽  
Function Approximation ◽  
System Modeling ◽  
Wavelet Network ◽  
Wavelet Networks ◽  
Simulation Results

The purpose of this paper is to present wavelet networks as a new scheme to model nonlinear systems. The capabilities of wavelet networks in function approximation make them appealing for system modeling. The wavelet networks presented are utilized in the dynamic modeling of a nonlinear servomechanism. A new wavelet network scheme is proposed for the identification of the nonlinearity in the servomechanism. Simulation results show the modeling performance of both schemes.

Using Improved Wavelet Networks in Image Compression

2012 ◽  
Vol 239-240 ◽  
pp. 1018-1021
Author(s):  
Wei Wei Xiao ◽  
Wei Jun Luan
Keyword(s):  
Image Compression ◽  
Activation Function ◽  
Basis Functions ◽  
Wavelet Basis ◽  
Wavelet Network ◽  
Wavelet Networks ◽  
Mexican Hat ◽  
Better Than

We proposed improved wavelet network and applied it to image compression. Activation function was selected automatically from three wavelet basis functions based on the effect of image compression. The three given wavelet basis functions were Morlet, Mexican-Hat and Different Of Gauss(DOG) wavelet basis functions respectively. The results show that the improved wavelet networks method is better than general wavelet networks in image compression.

Sign in / Sign up

Export Citation Format

Share Document