Formulation of an improved hyperspectral image processing algorithm for food quality monitoring
Sarawak's sago flour industry suffers from food fraud using whitening chemicals. This study uses Vis-NIR hyperspectral imaging and machine learning to rapidly detect adulterants. PLSR and PCR models excel in detecting calcium carbonate and alloxan monohydrate, respectively. A novel ensemble-bas...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
Curtin University
2024
|
| Online Access: | http://hdl.handle.net/20.500.11937/96327 |
| _version_ | 1848766137804783616 |
|---|---|
| author | Das, Mainak |
| author_facet | Das, Mainak |
| author_sort | Das, Mainak |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | Sarawak's sago flour industry suffers from food fraud using whitening chemicals. This study uses Vis-NIR hyperspectral imaging and machine learning to rapidly detect adulterants. PLSR and PCR models excel in detecting calcium carbonate and alloxan monohydrate, respectively. A novel ensemble-based, nonlinear model was developed to enhance prediction accuracy. This research underscores the potential of hyperspectral imaging and machine learning for sago flour quality control. |
| first_indexed | 2025-11-14T11:46:22Z |
| format | Thesis |
| id | curtin-20.500.11937-96327 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T11:46:22Z |
| publishDate | 2024 |
| publisher | Curtin University |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-963272024-11-13T04:35:48Z Formulation of an improved hyperspectral image processing algorithm for food quality monitoring Das, Mainak Sarawak's sago flour industry suffers from food fraud using whitening chemicals. This study uses Vis-NIR hyperspectral imaging and machine learning to rapidly detect adulterants. PLSR and PCR models excel in detecting calcium carbonate and alloxan monohydrate, respectively. A novel ensemble-based, nonlinear model was developed to enhance prediction accuracy. This research underscores the potential of hyperspectral imaging and machine learning for sago flour quality control. 2024 Thesis http://hdl.handle.net/20.500.11937/96327 Curtin University restricted |
| spellingShingle | Das, Mainak Formulation of an improved hyperspectral image processing algorithm for food quality monitoring |
| title | Formulation of an improved hyperspectral image processing algorithm for food quality monitoring |
| title_full | Formulation of an improved hyperspectral image processing algorithm for food quality monitoring |
| title_fullStr | Formulation of an improved hyperspectral image processing algorithm for food quality monitoring |
| title_full_unstemmed | Formulation of an improved hyperspectral image processing algorithm for food quality monitoring |
| title_short | Formulation of an improved hyperspectral image processing algorithm for food quality monitoring |
| title_sort | formulation of an improved hyperspectral image processing algorithm for food quality monitoring |
| url | http://hdl.handle.net/20.500.11937/96327 |