Principal component analysis of hyperspectral data for early detection of mould in cheeselets
The application of non-destructive process analytical technologies in the area of food science got a lot of attention the past years. In this work we used hyperspectral imaging to detect mould on milk agar and cheese. Principal component analysis is applied to hyperspectral data to localise and visu...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-01-01
|
| Series: | Current Research in Food Science |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2665927121000010 |
| _version_ | 1818353001528557568 |
|---|---|
| author | Jessica Farrugia Sholeem Griffin Vasilis P. Valdramidis Kenneth Camilleri Owen Falzon |
| author_facet | Jessica Farrugia Sholeem Griffin Vasilis P. Valdramidis Kenneth Camilleri Owen Falzon |
| author_sort | Jessica Farrugia |
| collection | DOAJ |
| description | The application of non-destructive process analytical technologies in the area of food science got a lot of attention the past years. In this work we used hyperspectral imaging to detect mould on milk agar and cheese. Principal component analysis is applied to hyperspectral data to localise and visualise mycelia on the samples’ surface. It is also shown that the PCA loadings obtained from a set of training samples can be applied to hyperspectral data from new test samples to detect the presence of mould on these. For both the agar and cheeselets, the first three principal components contained more than 99 % of the total variance. The spatial projection of the second principal component highlights the presence of mould on cheeselets. The proposed analysis methods can be adopted in industry to detect mould on cheeselets at an early stage and with further testing this application may also be extended to other food products. |
| first_indexed | 2024-12-13T19:02:35Z |
| format | Article |
| id | doaj.art-e70d696939574563bf43e57dbd759df5 |
| institution | Directory Open Access Journal |
| issn | 2665-9271 |
| language | English |
| last_indexed | 2024-12-13T19:02:35Z |
| publishDate | 2021-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Current Research in Food Science |
| spelling | doaj.art-e70d696939574563bf43e57dbd759df52022-12-21T23:34:39ZengElsevierCurrent Research in Food Science2665-92712021-01-0141827Principal component analysis of hyperspectral data for early detection of mould in cheeseletsJessica Farrugia0Sholeem Griffin1Vasilis P. Valdramidis2Kenneth Camilleri3Owen Falzon4Centre for Biomedical Cybernetics, University of Malta, Msida, MaltaCentre for Biomedical Cybernetics, University of Malta, Msida, Malta; Department of Food Sciences and Nutrition, University of Malta, Msida, Malta; Centre of Molecular Medicine and Biobanking, University of Malta, Msida, MaltaDepartment of Food Sciences and Nutrition, University of Malta, Msida, Malta; Centre of Molecular Medicine and Biobanking, University of Malta, Msida, MaltaCentre for Biomedical Cybernetics, University of Malta, Msida, Malta; Department of Systems & Control Engineering, Faculty of Engineering, University of Malta, Msida, MaltaCentre for Biomedical Cybernetics, University of Malta, Msida, Malta; Corresponding author.The application of non-destructive process analytical technologies in the area of food science got a lot of attention the past years. In this work we used hyperspectral imaging to detect mould on milk agar and cheese. Principal component analysis is applied to hyperspectral data to localise and visualise mycelia on the samples’ surface. It is also shown that the PCA loadings obtained from a set of training samples can be applied to hyperspectral data from new test samples to detect the presence of mould on these. For both the agar and cheeselets, the first three principal components contained more than 99 % of the total variance. The spatial projection of the second principal component highlights the presence of mould on cheeselets. The proposed analysis methods can be adopted in industry to detect mould on cheeselets at an early stage and with further testing this application may also be extended to other food products.http://www.sciencedirect.com/science/article/pii/S2665927121000010Hyperspectral imagingPrincipal component analysisAgarCheeselet |
| spellingShingle | Jessica Farrugia Sholeem Griffin Vasilis P. Valdramidis Kenneth Camilleri Owen Falzon Principal component analysis of hyperspectral data for early detection of mould in cheeselets Current Research in Food Science Hyperspectral imaging Principal component analysis Agar Cheeselet |
| title | Principal component analysis of hyperspectral data for early detection of mould in cheeselets |
| title_full | Principal component analysis of hyperspectral data for early detection of mould in cheeselets |
| title_fullStr | Principal component analysis of hyperspectral data for early detection of mould in cheeselets |
| title_full_unstemmed | Principal component analysis of hyperspectral data for early detection of mould in cheeselets |
| title_short | Principal component analysis of hyperspectral data for early detection of mould in cheeselets |
| title_sort | principal component analysis of hyperspectral data for early detection of mould in cheeselets |
| topic | Hyperspectral imaging Principal component analysis Agar Cheeselet |
| url | http://www.sciencedirect.com/science/article/pii/S2665927121000010 |
| work_keys_str_mv | AT jessicafarrugia principalcomponentanalysisofhyperspectraldataforearlydetectionofmouldincheeselets AT sholeemgriffin principalcomponentanalysisofhyperspectraldataforearlydetectionofmouldincheeselets AT vasilispvaldramidis principalcomponentanalysisofhyperspectraldataforearlydetectionofmouldincheeselets AT kennethcamilleri principalcomponentanalysisofhyperspectraldataforearlydetectionofmouldincheeselets AT owenfalzon principalcomponentanalysisofhyperspectraldataforearlydetectionofmouldincheeselets |