BWSpec™

 

SDK

 

BWID™

 

BWIQ™
  View our website for a more detailed description of this software.

BWIQ™

The Next Generation in Speed, Accuracy, and Performance

BWIQ™ chemometrics software package is intended for use with the i-Raman® and other high resolution Raman products. BWIQ™ is a multivariate analysis software package which can analyze spectral data and discover internal relationships between spectra and response data or spectra and sample classes. BWIQ™ combines traditional chemometric methods such as Partial Least Squares Regression (PLSR) and Principal Component Analysis (PCA), with new methods such as B&W Tek’s proprietary adaptive iteratively reweighted Penalized Least Squares (airPLS) algorithm for automatic baseline correction and Support Vector Machine (SVM) algorithms for non-linear datasets.

Applications: 

  • Multivariable Quantitative Analysis
  • Multivariable Classification Analysis
  • Exploratory Analysis
Key Features: 

  • Progressive structure and easy-to-follow work flow
  • Wide variety of regression and classification routines
  • Three different automatic sample partition algorithms
  • High performance and accuracy with the help of BLAS and LAPACK
  • High speed and less memory with sparse linear algebra algorithms
  • Chemometric Modeling Markup Language (CMML) for easy model storage and sharing
  • Innovative algorithms airPLS for baseline correction and Whittaker Penalized Least Squared algorithm for spectra smoothing
Main Functions: 

  • Automatic sample partition algorithms for sampling process
  • Various spectra preprocess algorithms, including automatic baseline correction airPLS (adaptive iteratively reweighted Penalized Least Squares); smoothing algorithms and spectra differential; as well as mean centering and auto scaling
  • Intuitive variable selection based on spectra as well as correlative coefficient.
  • Exploratory data analysis through Principle Component Analysis (PCA)
  • Regression analysis through various algorithms including MLR, PCR, PLS1, PLS2
  • Support Vector Machine Regression for non-linear datasets
  • Classification with cluster analysis and discriminant analysis with algorithms including SIMCA, PCA-MD, PLS-DA, SVC