Fang-Ming Liu

Fang-Ming Liu


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 May 2023 in Foods
Verified
Journal Article
Open access
PDF file
LWLI-YA WU
LI-YA WU
FLFang-Ming Liu
Fang-Ming Liu
SWSung-Shun Weng
Sung-Shun Weng
WLWen-Chou Lin
Wen-Chou Lin
Border management serves as a crucial control checkpoint for governments to regulate the quality and safety of imported food. In 2020, the first-generation ensemble learning prediction model (EL V.1) was introduced to Taiwan’s border food management. This model primarily assesses the risk of imported food by combining five algorithms to determine whether quality sampling should be performed on imported food at the border. In this study, a second-generation ensemble learning prediction model (EL V.2) was developed based on seven algorithms to enhance the “detection rate of unqualified cases” and improve the robustness of the model. In this study, Elastic Net was used to select the characteristic risk factors. Two algorithms were used to construct the new model: The Bagging-Gradient Boosting Machine and Bagging-Elastic Net. In addition, Fβ was used to flexibly control the sampling rate, improving the predictive performance and robustness of the model. The chi-square test was employed to compare the efficacy of “pre-launch (2019) random sampling inspection” and “post-launch (2020–2022) model prediction sampling inspection”. For cases recommended for inspection by the ensemble learning model and subsequently inspected, the unqualified rates were 5.10%, 6.36%, and 4.39% in 2020, 2021, and 2022, respectively, which were significantly higher (p < 0.001) compared with the random sampling rate of 2.09% in 2019. The prediction indices established by the confusion matrix were used to further evaluate the prediction effects of EL V.1 and EL V.2, and the EL V.2 model exhibited superior predictive performance compared with EL V.1, and both models outperformed random sampling.

11 August 2024 in Foods
Verified
Journal Article
Open access
PDF file
LWLI-YA WU
LI-YA WU
FLFang-Ming Liu
Fang-Ming Liu
WLWen-Chou Lin
Wen-Chou Lin
JQJing-Ting Qiu
Jing-Ting Qiu
HLHsu-Yang Lin
Hsu-Yang Lin
KLKing-Fu Lin
King-Fu Lin
Considering the frequency of ethylene oxide (EtO) residues found in food, the health effects of EtO have become a concern. Between 2022 and 2023, 489 products were inspected using the purposive sampling method in Taiwan, and nine unqualified products were found to have been imported; subsequently, border control measures were enhanced. To ensure the safety of all imported foods, the current study used the K-means clustering method for identifying EtO residues in food. Data on finished products and raw materials with EtO residues from international public opinion bulletins were collected for analysis. After matching them with the Taiwan Food Cloud, 90 high-risk food items with EtO residues and 1388 manufacturers were screened. The Taiwan Food and Drug Administration set up border controls and grouped the manufacturers using K-means clustering in the unsupervised learning algorithm. For this study, 37 manufacturers with priority inspections and 52 high-risk finished products and raw materials with residual EtO were selected for inspection. While EtO was not detected, the study concluded the following: 1. Using international food safety alerts to strengthen border control can effectively ensure domestic food safety; 2. K-means clustering can validate the risk-based purposive sampling results to ensure food safety and reduce costs.