TY - JOUR
T1 - Modelling boundary shear stress distribution in open channels using a face recognition technique
AU - Martinez-Vazquez, Pedro
AU - Sharifi, Soroosh
N1 - The paper presents a numerical method for the prediction of shear stress distributions in open channels based on image recognition techniques. The modelling approach merges an algorithm for the recognition of human faces that was developed in the field of neuroscience, with a technique to transform one-dimensional data series into two-dimensional images. This enables to identify intrinsic features of the data which otherwise would not be possible to appreciate in its original state. The model in its current state can be used to tackle a wider range of engineering problems which enhances its potential impact as is adopted by scientists.
PY - 2017/3/1
Y1 - 2017/3/1
N2 - This paper describes a novel application of a pattern recognition technique for predicting boundary shear stress distribution in open channels. In this approach, a synthetic database of images representing normalized shear stress distributions is formed from a training data set using recurrence plot analysis. The face recognition algorithm is then employed to synthesize the recurrence plots and transform the original database into short-dimension vectors containing similarity weights proportional to the principal components of the distribution of images. These vectors capture the intrinsic properties of the boundary shear stress distribution of the cases in the training set, and are sensitive to variations of the corresponding hydraulic parameters. The process of transforming one-dimensional data series into vectors of weights is invertible, and therefore, shear stress distributions for unseen cases can be predicted. The developed method is applied to predict boundary shear stress distributions in smooth trapezoidal and circular channels. The results show a cross correlation coefficient above 92%, mean square errors within 0.04% and 4.48%, and average shear stress fluctuations within 2% and 5%, thus, indicating that the proposed method is capable of providing accurate estimations of the boundary shear stress distribution in open channels.
AB - This paper describes a novel application of a pattern recognition technique for predicting boundary shear stress distribution in open channels. In this approach, a synthetic database of images representing normalized shear stress distributions is formed from a training data set using recurrence plot analysis. The face recognition algorithm is then employed to synthesize the recurrence plots and transform the original database into short-dimension vectors containing similarity weights proportional to the principal components of the distribution of images. These vectors capture the intrinsic properties of the boundary shear stress distribution of the cases in the training set, and are sensitive to variations of the corresponding hydraulic parameters. The process of transforming one-dimensional data series into vectors of weights is invertible, and therefore, shear stress distributions for unseen cases can be predicted. The developed method is applied to predict boundary shear stress distributions in smooth trapezoidal and circular channels. The results show a cross correlation coefficient above 92%, mean square errors within 0.04% and 4.48%, and average shear stress fluctuations within 2% and 5%, thus, indicating that the proposed method is capable of providing accurate estimations of the boundary shear stress distribution in open channels.
KW - boundary shear stress
KW - data modelling
KW - face recognition
KW - recurrence plot anaysis
KW - open channel
U2 - 10.2166/hydro.2016.068
DO - 10.2166/hydro.2016.068
M3 - Article
SN - 1464-7141
VL - 19
SP - 157
EP - 172
JO - Journal of Hydroinformatics
JF - Journal of Hydroinformatics
IS - 2
ER -