Monitoring food safety risks using machines learning techniques
| dc.contributor.author | Bouti, Hadil | |
| dc.contributor.author | Zerrouak, Fatma Zohra | |
| dc.contributor.author | Tahar, Mehenni: Supervisor | |
| dc.date.accessioned | 2024-07-09T11:05:52Z | |
| dc.date.available | 2024-07-09T11:05:52Z | |
| dc.date.issued | 2024-06 | |
| dc.description.abstract | In this thesis, six machine learning algorithms (simple linear regression, polynomial regression, logistic regression, random forests, decision tree, and support vector machine) were explored to predict and classify food safety risks. A comprehensive dataset including price data and weather data affecting food safety risks was collected and used to train and test the models. Performance metrics such as accuracy, precision, and recall were used to evaluate the models. The results showed that all algorithms performed well, but the polynomial regression model achieved the best correlation coefficient for prediction models, while the decision tree achieved the highest accuracy for classification models. This research highlights the effectiveness of machine learning in predicting and classifying food safety risks and underscores the importance of leveraging advanced techniques to mitigate these risks and ensure food safety for consumers. | |
| dc.identifier.uri | https://dspace.univ-msila.dz/handle/123456789/43466 | |
| dc.language.iso | en | |
| dc.publisher | Mohamed Boudiaf University of M'sila | |
| dc.subject | Food security | |
| dc.subject | machine learning | |
| dc.subject | food safety | |
| dc.subject | risk prediction | |
| dc.subject | regression | |
| dc.subject | classification | |
| dc.title | Monitoring food safety risks using machines learning techniques | |
| dc.type | Thesis |