Refine
H-BRS Bibliography
- yes (14)
Departments, institutes and facilities
Document Type
- Article (10)
- Conference Object (4)
Keywords
- Chemometrics (3)
- Classification (2)
- Discriminant analysis (2)
- Hyperspectral image (2)
- Raman microscopy (2)
- Raman-microspectroscopy (2)
- SERS (2)
- classification (2)
- discriminant analysis (2)
- food-related bacteria (2)
- image fusion (2)
- pansharpening (2)
- stress response (2)
- AuNPs (1)
- Branch and cut (1)
- Chemical imaging (1)
- E. coli (1)
- GC/MS (1)
- IR microspectroscopy (1)
- IR-microspectroscopy (1)
- Integer programming (1)
- MAP (1)
- Meat-associated Microorganisms (1)
- Molecular dynamics (1)
- Molecular simulation (1)
- Molekulardynamik (1)
- Molekulare Simulation (1)
- Monte-Carlo simulation (1)
- Monte-Carlo-Simulation (1)
- Multimodal hyperspectral data (1)
- PDSTSP (1)
- Parallel drone scheduling traveling salesman problem (1)
- Pathogenic Bacteria (1)
- Pattern recognition (1)
- Poultry (1)
- Principal component analysis (1)
- Ps. fluorescens (1)
- Raman Spectroscopy (1)
- Raman spectroscopy (1)
- Separation algorithm (1)
- Spoilage bacteria (1)
- Supervised classification (1)
- Thermodynamic data (1)
- Thermodynamische Stoffdaten (1)
- TiO2-coatings (1)
- VOC (1)
- Vibrational microspectroscopy (1)
- bacteria (1)
- brightfield microscopy (1)
- chemometrics (1)
- coffee ring effect (1)
- food safety (1)
- multiresolution analysis (1)
The application of Raman and infrared (IR) microspectroscopy is leading to hyperspectral data containing complementary information concerning the molecular composition of a sample. The classification of hyperspectral data from the individual spectroscopic approaches is already state-of-the-art in several fields of research. However, more complex structured samples and difficult measuring conditions might affect the accuracy of classification results negatively and could make a successful classification of the sample components challenging. This contribution presents a comprehensive comparison in supervised pixel classification of hyperspectral microscopic images, proving that a combined approach of Raman and IR microspectroscopy has a high potential to improve classification rates by a meaningful extension of the feature space. It shows that the complementary information in spatially co-registered hyperspectral images of polymer samples can be accessed using different feature extraction methods and, once fused on the feature-level, is in general more accurately classifiable in a pattern recognition task than the corresponding classification results for data derived from the individual spectroscopic approaches.
Surface-enhanced Raman spectroscopy (SERS) with subsequent chemometric evaluation was performed for the rapid and non-destructive differentiation of seven important meat-associated microorganisms, namely Brochothrix thermosphacta DSM 20171, Pseudomonas fluorescens DSM 4358, Salmonella enterica subsp. enterica sv. Enteritidis DSM 14221, Listeria monocytogenes DSM 19094, Micrococcus luteus DSM 20030, Escherichia coli HB101 and Bacillus thuringiensis sv. israelensis DSM 5724. A simple method for collecting spectra from commercial paper-based SERS substrates without any laborious pre-treatments was used. In order to prepare the spectroscopic data for classification at genera level with a subsequent chemometric evaluation consisting of principal component analysis and discriminant analysis, a pre-processing method with spike correction and sum normalisation was performed. Because of the spike correction rather than exclusion, and therefore the use of a balanced data set, the multivariate analysis of the data is significantly resilient and meaningful. The analysis showed that the differentiation of meat-associated microorganisms and thereby the detection of important meat-related pathogenic bacteria was successful on genera level and a cross-validation as well as a classification of ungrouped data showed promising results, with 99.5 % and 97.5 %, respectively.
Because the robust and rapid determination of spoilage microorganisms is becoming increasingly important in industry, the use of IR microspectroscopy, and the establishment of robust and versatile chemometric models for data processing and classification, is gaining importance. To further improve the chemometric models, bacterial stress responses were induced, to study the effect on the IR spectra and to improve the chemometric model. Thus, in this work, nine important food-relevant microorganisms were subjected to eight stress conditions, besides the regular culturing as a reference. Spectral changes compared to normal growth conditions without stressors were found in the spectral regions of 900–1500 cm−1 and 1500–1700 cm−1. These differences might stem from changes in the protein secondary structure, exopolymer production, and concentration of nucleic acids, lipids, and polysaccharides. As a result, a model for the discrimination of the studied microorganisms at the genus, species and strain level was established, with an accuracy of 96.6%. This was achieved despite the inclusion of various stress conditions and times after incubation of the bacteria. In addition, a model was developed for each individual microorganism, to separate each stress condition or regular treatment with 100% accuracy.