Parametric Identification of Ship Maneuvering Models by Using Support Vector Machines

2009 ◽  
Vol 53 (01) ◽  
pp. 19-30 ◽  
Author(s):  
W. L. Luo ◽  
Z. J. Zou
Keyword(s):  
Support Vector Machines ◽  
Predictive Ability ◽  
Parametric Identification ◽  
Inner Product ◽  
Support Vector ◽  
Identification Algorithm ◽  
Hydrodynamic Coefficients ◽  
Ship Maneuvering ◽  
Vector Machines ◽  
Maneuvering Motion

System identification combined with free-running model tests or full-scale trials is one of the effective methods to determine the hydrodynamic coefficients in the mathematical models of ship maneuvering motion. By analyzing the available data, including rudder angle, surge speed, sway speed, yaw rate, and so forth, a method based on support vector machines (SVM) to estimate the hydrodynamic coefficients is proposed for conventional surface ships. The coefficients are contained in the expansion of the inner product of a linear kernel function. Predictions of maneuvering motion are conducted by using the parameters identified. The results of identification and simulation demonstrate the validity of the identification algorithm proposed. The simultaneous drift and multicollinearity are diminished by introducing an additional ramp signal to the training samples. Comparison between the simulated and predicted motion variables from different maneuvers shows good predictive ability of the trained SVM.

Parameter Identification of Ship Maneuvering Model Based on Support Vector Machines and Particle Swarm Optimization

2016 ◽  
Vol 138 (3) ◽  
Author(s):  
Weilin Luo ◽  
C. Guedes Soares ◽  
Zaojian Zou
Keyword(s):  
Particle Swarm Optimization ◽  
Support Vector Machines ◽  
Difference Method ◽  
Particle Swarm ◽  
Support Vector ◽  
Ship Maneuvering ◽  
Swarm Optimization ◽  
Hydrodynamic Derivatives ◽  
Vector Machines ◽  
Maneuvering Motion

Combined with the free-running model tests of KVLCC ship, the system identification (SI) based on support vector machines (SVM) is proposed for the prediction of ship maneuvering motion. The hydrodynamic derivatives in an Abkowitz model are determined by the Lagrangian factors and the support vectors in the SVM regression model. To obtain the optimized structural factors in SVM, particle swarm optimization (PSO) is incorporated into SVM. To diminish the drift of hydrodynamic derivatives after regression, a difference method is adopted to reconstruct the training samples before identification. The validity of the difference method is verified by correlation analysis. Based on the Abkowitz mathematical model, the simulation of ship maneuvering motion is conducted. Comparison between the predicted results and the test results demonstrates the validity of the proposed methods in this paper.

Blind Prediction of Ship Maneuvering by Using Support Vector Machines

2010 ◽  
Author(s):  
Wei-lin Luo ◽  
Zao-jian Zou
Keyword(s):  
Support Vector Machines ◽  
Black Box ◽  
Support Vector ◽  
Nonlinear Functions ◽  
Ship Maneuvering ◽  
Vector Machines ◽  
Turning Test ◽  
Yaw Moment ◽  
Rudder Angle ◽  
Maneuvering Motion

Support Vector Machines (SVM) based system identification is applied to predict ship maneuvering motion. Different from the prediction methods based on the explicit mathematical model of ship maneuvering motion, the black-box model of ship maneuvering motion is constructed and used to predict ship maneuvering motion. With the rudder angle and the variables of maneuvering motion as inputs and the hydrodynamic forces as outputs, the complicated nonlinear functions in the Abkowitz model are identified; and the surge force, sway force and yaw moment are predicted blindly by using the functions identified. Taking turning test as example, with the rudder angle as inputs and the maneuverability parameters of turning circles as outputs, the input-output mappings are identified and the maneuverability parameters such as the advance, the transfer and the tactical diameter are also predicted blindly by using the identified mappings.

scholarly journals A Novel Homogenous Hybridization Scheme for Performance Improvement of Support Vector Machines Regression in Reservoir Characterization

2016 ◽  
Vol 2016 ◽  
pp. 1-10 ◽  
Author(s):  
Kabiru O. Akande ◽  
Taoreed O. Owolabi ◽  
Sunday O. Olatunji ◽  
AbdulAzeez Abdulraheem
Keyword(s):  
Support Vector Machines ◽  
Reservoir Characterization ◽  
Petroleum Industry ◽  
Predictive Ability ◽  
Extraction Process ◽  
Superior Performance ◽  
Support Vector ◽  
Prediction Ability ◽  
Intelligent Algorithms ◽  
Vector Machines

Hybrid computational intelligence is defined as a combination of multiple intelligent algorithms such that the resulting model has superior performance to the individual algorithms. Therefore, the importance of fusing two or more intelligent algorithms to achieve better performance cannot be overemphasized. In this work, a novel homogenous hybridization scheme is proposed for the improvement of the generalization and predictive ability of support vector machines regression (SVR). The proposed and developed hybrid SVR (HSVR) works by considering the initial SVR prediction as a feature extraction process and then employs the SVR output, which is the extracted feature, as its sole descriptor. The developed hybrid model is applied to the prediction of reservoir permeability and the predicted permeability is compared to core permeability which is regarded as standard in petroleum industry. The results show that the proposed hybrid scheme (HSVR) performed better than the existing SVR in both generalization and prediction ability. The outcome of this research will assist petroleum engineers to effectively predict permeability of carbonate reservoirs with higher degree of accuracy and will invariably lead to better reservoir. Furthermore, the encouraging performance of this hybrid will serve as impetus for further exploring homogenous hybrid system.

MONOTONIC SUPPORT VECTOR MACHINES FOR CREDIT RISK RATING

2009 ◽  
Vol 05 (03) ◽  
pp. 557-570 ◽  
Author(s):  
MICHAEL DOUMPOS ◽  
CONSTANTIN ZOPOUNIDIS
Keyword(s):  
Support Vector Machines ◽  
Pattern Classification ◽  
Credit Rating ◽  
Monotone Function ◽  
Predictive Ability ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Probability Of Default ◽  
Modeling Framework ◽  
Vector Machines

Credit rating models are widely used by banking institutions to assess the creditworthiness of credit applicants and to estimate the probability of default. Several pattern classification algorithms are used for the development of such models. In contrast to other pattern classification tasks, however, credit rating models are not only expected to provide accurate predictions, but also to make clear economic sense. Within this context, the estimated probability of default is often required to be a monotone function of the independent variables. Most machine learning techniques do not take this requirement into account. In this paper, monotonicity hints are used to address this issue within the modeling framework of support vector machines (SVM), which have become increasingly popular in this field. Non-linear SVM credit rating models are developed with linear programming, taking into account the monotonicity requirement. The obtained results indicate that the introduction of monotonicity hints improves the predictive ability of the models.

scholarly journals Fuzzy c-Means Clustering Using Kernel Functions in Support Vector Machines

2003 ◽  
Vol 7 (1) ◽  
pp. 25-30 ◽  
Author(s):  
Sadaaki Miyamoto ◽  
◽  
Daisuke Suizu ◽  
Keyword(s):  
Support Vector Machines ◽  
Dimensional Space ◽  
Clustering Algorithms ◽  
Kernel Functions ◽  
Inner Product ◽  
Support Vector ◽  
Fuzzy C Means ◽  
Vector Machines ◽  
Minimization Algorithms ◽  
Fuzzy C Means Clustering

We studied clustering algorithms of fuzzy c-means using a kernel to represent an inner product for mapping into high-dimensional space. Such kernels have been studied in support vector machines used by many researchers in pattern classification. Algorithms of fuzzy c-means are transformed into kernel-based methods by changing objective functions, whereby new iterative minimization algorithms are derived. Numerical examples show that clusters that cannot be obtained without a kernel are generated.

Sign in / Sign up

Export Citation Format

Share Document