TY - JOUR
T1 - A system for classification of time-series data from industrial non-destructive device
AU - Perez-Benitez, J. A.
AU - Padovese, L. R.
N1 - Funding Information:
The authors would like to thank the financial support of Brazilian agencies FAPESP/ Proc . No. 2008/10859-0 and CNPq/proc . No. 490617/2008-5 .
PY - 2013/3
Y1 - 2013/3
N2 - This work proposes a system for classification of industrial steel pieces by means of magnetic nondestructive device. The proposed classification system presents two main stages, online system stage and off-line system stage. In online stage, the system classifies inputs and saves misclassification information in order to perform posterior analyses. In the off-line optimization stage, the topology of a Probabilistic Neural Network is optimized by a Feature Selection algorithm combined with the Probabilistic Neural Network to increase the classification rate. The proposed Feature Selection algorithm searches for the signal spectrogram by combining three basic elements: a Sequential Forward Selection algorithm, a Feature Cluster Grow algorithm with classification rate gradient analysis and a Sequential Backward Selection. Also, a trash-data recycling algorithm is proposed to obtain the optimal feedback samples selected from the misclassified ones.
AB - This work proposes a system for classification of industrial steel pieces by means of magnetic nondestructive device. The proposed classification system presents two main stages, online system stage and off-line system stage. In online stage, the system classifies inputs and saves misclassification information in order to perform posterior analyses. In the off-line optimization stage, the topology of a Probabilistic Neural Network is optimized by a Feature Selection algorithm combined with the Probabilistic Neural Network to increase the classification rate. The proposed Feature Selection algorithm searches for the signal spectrogram by combining three basic elements: a Sequential Forward Selection algorithm, a Feature Cluster Grow algorithm with classification rate gradient analysis and a Sequential Backward Selection. Also, a trash-data recycling algorithm is proposed to obtain the optimal feedback samples selected from the misclassified ones.
KW - Carbon content
KW - MBN decorrelation
KW - Non-destructive methods
KW - Plastic deformation
UR - http://www.scopus.com/inward/record.url?scp=84873988049&partnerID=8YFLogxK
U2 - 10.1016/j.engappai.2012.09.006
DO - 10.1016/j.engappai.2012.09.006
M3 - Artículo
SN - 0952-1976
VL - 26
SP - 974
EP - 983
JO - Engineering Applications of Artificial Intelligence
JF - Engineering Applications of Artificial Intelligence
IS - 3
ER -