Prediction of Safety Risk Levels of Benzopyrene Residues in Edible Oils in China Based on the Variable-Weight Combined LSTM-XGBoost Prediction Model
To assess and predict the food safety risk of benzopyrene (BaP) in edible oils in China, this study collected national sampling data of edible oils from 20 Chinese provinces and their prefectures in 2019, and constructed a risk assessment model of BaP in edible oils with consumption data. Initially,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Jezik: | English |
| Izdano: |
MDPI AG
2023-06-01
|
| Serija: | Foods |
| Teme: | |
| Online dostop: | https://www.mdpi.com/2304-8158/12/11/2241 |
| _version_ | 1827739520389349376 |
|---|---|
| author | Cheng Hao Qingchuan Zhang Shimin Wang Tongqiang Jiang Wei Dong |
| author_facet | Cheng Hao Qingchuan Zhang Shimin Wang Tongqiang Jiang Wei Dong |
| author_sort | Cheng Hao |
| collection | DOAJ |
| description | To assess and predict the food safety risk of benzopyrene (BaP) in edible oils in China, this study collected national sampling data of edible oils from 20 Chinese provinces and their prefectures in 2019, and constructed a risk assessment model of BaP in edible oils with consumption data. Initially, the k-means algorithm was used for risk classification; then the data were pre-processed and trained to predict the data using the Long Short-Term Memory (LSTM) and the eXtreme Gradient Boosting (XGBoost) models, respectively, and finally, the two models were combined using the inverse error method. To test the effectiveness of the prediction model, this study experimentally validated the model according to five evaluation metrics: root mean square error (RMSE), mean absolute error (MAE), precision, recall, and F1 score. The variable-weight combined LSTM-XGBoost prediction model proposed in this paper achieved a precision of 94.62%, and the F1 score value reached 95.16%, which is significantly better than other neural network models; the results demonstrate that the prediction model has certain stability and feasibility. Overall, the combined model used in this study not only improves the accuracy but also enhances the practicality, real-time capabilities, and expandability of the model. |
| first_indexed | 2024-03-11T03:07:53Z |
| format | Article |
| id | doaj.art-b691b9a0253b4b51a59428470eae71a1 |
| institution | Directory Open Access Journal |
| issn | 2304-8158 |
| language | English |
| last_indexed | 2024-03-11T03:07:53Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Foods |
| spelling | doaj.art-b691b9a0253b4b51a59428470eae71a12023-11-18T07:52:11ZengMDPI AGFoods2304-81582023-06-011211224110.3390/foods12112241Prediction of Safety Risk Levels of Benzopyrene Residues in Edible Oils in China Based on the Variable-Weight Combined LSTM-XGBoost Prediction ModelCheng Hao0Qingchuan Zhang1Shimin Wang2Tongqiang Jiang3Wei Dong4National Engineering Research Centre for Agri-Product Quality Traceability, Beijing Technology and Business University, Beijing 100048, ChinaNational Engineering Research Centre for Agri-Product Quality Traceability, Beijing Technology and Business University, Beijing 100048, ChinaNational Engineering Research Centre for Agri-Product Quality Traceability, Beijing Technology and Business University, Beijing 100048, ChinaNational Engineering Research Centre for Agri-Product Quality Traceability, Beijing Technology and Business University, Beijing 100048, ChinaNational Engineering Research Centre for Agri-Product Quality Traceability, Beijing Technology and Business University, Beijing 100048, ChinaTo assess and predict the food safety risk of benzopyrene (BaP) in edible oils in China, this study collected national sampling data of edible oils from 20 Chinese provinces and their prefectures in 2019, and constructed a risk assessment model of BaP in edible oils with consumption data. Initially, the k-means algorithm was used for risk classification; then the data were pre-processed and trained to predict the data using the Long Short-Term Memory (LSTM) and the eXtreme Gradient Boosting (XGBoost) models, respectively, and finally, the two models were combined using the inverse error method. To test the effectiveness of the prediction model, this study experimentally validated the model according to five evaluation metrics: root mean square error (RMSE), mean absolute error (MAE), precision, recall, and F1 score. The variable-weight combined LSTM-XGBoost prediction model proposed in this paper achieved a precision of 94.62%, and the F1 score value reached 95.16%, which is significantly better than other neural network models; the results demonstrate that the prediction model has certain stability and feasibility. Overall, the combined model used in this study not only improves the accuracy but also enhances the practicality, real-time capabilities, and expandability of the model.https://www.mdpi.com/2304-8158/12/11/2241risk assessmentLSTMXGBoostrisk predictionedible oilBaP |
| spellingShingle | Cheng Hao Qingchuan Zhang Shimin Wang Tongqiang Jiang Wei Dong Prediction of Safety Risk Levels of Benzopyrene Residues in Edible Oils in China Based on the Variable-Weight Combined LSTM-XGBoost Prediction Model Foods risk assessment LSTM XGBoost risk prediction edible oil BaP |
| title | Prediction of Safety Risk Levels of Benzopyrene Residues in Edible Oils in China Based on the Variable-Weight Combined LSTM-XGBoost Prediction Model |
| title_full | Prediction of Safety Risk Levels of Benzopyrene Residues in Edible Oils in China Based on the Variable-Weight Combined LSTM-XGBoost Prediction Model |
| title_fullStr | Prediction of Safety Risk Levels of Benzopyrene Residues in Edible Oils in China Based on the Variable-Weight Combined LSTM-XGBoost Prediction Model |
| title_full_unstemmed | Prediction of Safety Risk Levels of Benzopyrene Residues in Edible Oils in China Based on the Variable-Weight Combined LSTM-XGBoost Prediction Model |
| title_short | Prediction of Safety Risk Levels of Benzopyrene Residues in Edible Oils in China Based on the Variable-Weight Combined LSTM-XGBoost Prediction Model |
| title_sort | prediction of safety risk levels of benzopyrene residues in edible oils in china based on the variable weight combined lstm xgboost prediction model |
| topic | risk assessment LSTM XGBoost risk prediction edible oil BaP |
| url | https://www.mdpi.com/2304-8158/12/11/2241 |
| work_keys_str_mv | AT chenghao predictionofsafetyrisklevelsofbenzopyreneresiduesinedibleoilsinchinabasedonthevariableweightcombinedlstmxgboostpredictionmodel AT qingchuanzhang predictionofsafetyrisklevelsofbenzopyreneresiduesinedibleoilsinchinabasedonthevariableweightcombinedlstmxgboostpredictionmodel AT shiminwang predictionofsafetyrisklevelsofbenzopyreneresiduesinedibleoilsinchinabasedonthevariableweightcombinedlstmxgboostpredictionmodel AT tongqiangjiang predictionofsafetyrisklevelsofbenzopyreneresiduesinedibleoilsinchinabasedonthevariableweightcombinedlstmxgboostpredictionmodel AT weidong predictionofsafetyrisklevelsofbenzopyreneresiduesinedibleoilsinchinabasedonthevariableweightcombinedlstmxgboostpredictionmodel |