Lorentz JÄNTSCHI (lori) works ?id=243
- [id] => 243
- [recorddate] => 2013:06:16:11:22:51
- [lastupdate] => 2013:06:16:11:22:51
- [type] => article
- [place] => Cluj-Napoca, Romania
- [subject] => chemistry - organic; mathematics - modeling
- [relatedworks] =>
- 0 (highest):
- Topological substituent descriptors, ?id=17
- Centrality of some cubic graphs on 16 vertices, ?id=229

- 2 (average):
- Computer assisted geometry optimization for in silico modeling, ?id=244
- Kinetic study of saccharomyces pastorianus (carlsbergensis) multiplication, ?id=246
- Distribution fitting 12. Sampling distribution of compounds abundance from plant species measured by instrumentation. application to plants metabolism classification, ?id=250
- Quantum mechanics study on a series of steroids relating separation with structure, ?id=257

- 3 (low):
- Artificial photosynthesis: porphyrins-fullerene molecular complex, ?id=277

- 4 (some):
- Numerical simulation of concurent diffusion and reaction, ?id=28
- Dependence between determination coefficient and number of regressors: a case study on retention times of mycotoxins, ?id=235

- [file] => ?f=243
- [mime] => application/pdf
- [size] => 272240
- [pubname] => Applied Medical Informatics
- [pubinfo] => SRIMA
- [pubkey] => ISSN 1224-5593, eISSN 2067-7855
- [workinfo] => 29(3): 1-10
- [year] => 2011
- [title] => Neural network on photodegradation of octylphenol using natural and artificial UV radiation
- [authors] => Dana M. POPA, Letiţia OPREAN, Lorentz JÄNTSCHI
- [abstract] =>

The present paper comes up with an experimental design meant to point out the factors interfering in octylphenol’s degradation in surface waters under solar radiation, underlining each factor’s influence on the process observable (concentration of p-octylphenol). Multiple linear regression analysis and artificial neural network (Multi-Layer Perceptron type) were applied in order to obtain a mathematical model capable to explain the action of UV-light upon synthetic solutions of OP in ultra-pure water (MilliQ type). Neural network proves to be the most efficient method in predicting the evolution of OP concentration during photodegradation process. Thus, determination in neural network’s case has almost double value versus the regression analysis.
- [keywords] => octylphenol; photodegradation; regression analysis; backward stepwise method; neural network; multilayer perceptron
- [acknowledgment] => The study was supported by POSDRU/89/1.5/S/62371 through a fellowship for L. Jäntschi.