Mathematics
7 years ago

New method speeds up parameter estimation without compromising accuracy.

International Journal of Applied Mathematics and Machine Learning
ON MIXED TOTAL LEAST SQUARES FOR PARAMETER ESTIMATION
Cuiping Guo, Junhuan Peng, Chuantao Li

Paper Summary

Related papers

Theme background image
Computer Science
a year ago

New formula makes dual least-squares solutions more accurate than ever!

Matrix Algorithms
Optimization Techniques
Least Squares
2 views
Theme background image
Computer Science
4 years ago

Total least squares estimation more vulnerable to data errors than least squares.

Expert Systems
Inertial Navigation
Smart Transducers
2 views
Theme background image
Mathematics
8 years ago

New algorithm improves accuracy of data analysis for better decision-making.

Least Squares
Inertial Navigation
Grey System Theory
1 view

A new method called mixed weighted total least squares (MWTLS) was developed to estimate parameters in a model with errors-in-variables. This method improves computing speed while keeping certain columns of the coefficient matrix unchanged. The researchers created an iterative algorithm based on MWTLS and tested it with a simulated example, showing its effectiveness in parameter estimation.