Applying machine learning methods in studying relationships between mouthfeel and microstructure of oat bread
| Autor: | J.T. Lindgren, Juho Rousu, Karin Autio, Marjatta Salmenkallio-Marttila, Katariina Roininen, Liisa Lähteenmäki |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2004 |
| Předmět: |
Materials science
Starch Pharmaceutical Science Machine learning computer.software_genre 01 natural sciences Sensory analysis Texture (geology) 010104 statistics & probability Mouthfeel Starch gelatinization chemistry.chemical_compound 0404 agricultural biotechnology Microscopy 0101 mathematics 2. Zero hunger chemistry.chemical_classification business.industry food and beverages 04 agricultural and veterinary sciences Microstructure 040401 food science Gluten chemistry Artificial intelligence business computer Food Science |
| Zdroj: | Salmenkallio-Marttila, M, Roininen, K, Lindgren, J T, Rousu, J, Autio, K & Lähteenmäki, L 2004, ' Applying machine learning methods in studying relationships between mouthfeel and microstructure of oat bread ', Journal of Texture Studies, vol. 35, no. 3, pp. 225-250 . https://doi.org/10.1111/j.1745-4603.2004.tb00835.x |
| ISSN: | 1745-4603 0022-4901 |
| Popis: | The aim was to study whether machine learning can be applied in analysing microstructure of food from microscopy images and whether the state of macromolecules, protein and starch, can be related to sensory mouthfeel. Addition of gluten and transglutaminase modified the microstructure and mouthfeel of five oat bread samples. Light microscopy, instrumental texture profile analysis and descriptive sensory analysis were used to analyse the test breads. Digital image analysis was used to obtain numerical data on starch and protein phases in the breads. Degree of starch gelatinization and protein network properties were extracted from microscopy images by expert ratings. Many of the bread sensory properties could be predicted using instrumental texture and image analysis features. Machine learning of degree of starch gelatinization and protein network structure properties from expert classified microscope images was studied. Color histograms and co-occurrence matrix statistics were suitable preprocessing techniques for the images. In both starch gelatinization and protein network structure classification, the prediction error of an induced model tree was lower than the standard deviation between independent predictions given by experts. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|