Adaptive blind separation of independent sources: a deflation approach
Signal Processing
A fast fixed-point algorithm for independent component analysis
Neural Computation
AQTR '08 Proceedings of the 2008 IEEE International Conference on Automation, Quality and Testing, Robotics - Volume 03
A blind source separation technique using second-order statistics
IEEE Transactions on Signal Processing
Hi-index | 0.00 |
Usually, dam monitoring systems are based on both boundary conditions (temperature, rainfall, water level, etc.) and structural responses. Statistical analysis tools are widely used to determine eventual unwanted behaviors. The main drawback of this approach is that the structural response quantities are related to the external loads using analytical functions, whose parameters do not have physical meaning. In this paper a new approach to solve this problem, based on a neural network learning rule for Blind Source Separation (BSS), to find out the contributions of the dam external loads is presented and applied in a case study for a concrete dam.