𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Non-linear modelling of chemical data by combinations of linear and neural net methods

✍ Scribed by Beata Walczak; Wolfhard Wegscheider

Publisher
Elsevier Science
Year
1993
Tongue
English
Weight
817 KB
Volume
283
Category
Article
ISSN
0003-2670

No coin nor oath required. For personal study only.

✦ Synopsis

The combinations of classical bilinear models and neural nets, extended to neural net models on residuals from partial least squares (PLS) are discussed. The performances of principal component regression (PCR), PLS, neural networks (NN), principal component analysis (PCA)-NN and PLS residuals-NN are compared on simulated data, near-infrared data and quantitative structure-activity relationship data.

πŸ“œ SIMILAR VOLUMES

Non-linear statistical modelling of high
Non-linear statistical modelling of high frequency ground ozone data
✍ Alessandro FassΓ²; Ilia Negri πŸ“‚ Article πŸ“… 2002 πŸ› John Wiley and Sons 🌐 English βš– 156 KB

## Abstract The problem of describing hourly data of ground ozone is considered. The complexity of high frequency environmental data dynamics often requires models covering covariates, multiple frequency periodicities, long memory, non‐linearity and heteroscedasticity. For these reasons we introduc

Modeling and classification of non-linea
Modeling and classification of non-linear systems using neural networks--II. A preliminary experiment
✍ K. Worden; G.R. Tomlinson; W. Lim; G. Sauer πŸ“‚ Article πŸ“… 1994 πŸ› Elsevier Science 🌐 English βš– 679 KB

In the first part of this study, a method for classifying non-linear systems using neural networks was proposed and validated using data from numerical simulation. In order to extend this validation to experimental data, a system was required with a repeatable non-linearity of controllable severity,