Prediction of Escherichia coli Bacterial and Coliforms on Plants through Artificial Neural Network
The researchers investigated the efficiency of several disinfectants in reducing coliforms and Escherichia coli rates on carrots and lettuce, as well as using ANN to calculate the bacteria on the edible plants. Fresh greens leaves are cleaned and dried in sterile water. Vaccinated leafy greens veget...
Saved in:
Published in | Advances in materials science and engineering Vol. 2022; pp. 1 - 13 |
---|---|
Main Authors | , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
New York
Hindawi
2022
John Wiley & Sons, Inc Wiley |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The researchers investigated the efficiency of several disinfectants in reducing coliforms and Escherichia coli rates on carrots and lettuce, as well as using ANN to calculate the bacteria on the edible plants. Fresh greens leaves are cleaned and dried in sterile water. Vaccinated leafy greens vegetables were immersed in a vessel and treated with chlorine, and we choose plant extracts to evaluate the impact of the extraction. The pH measurement was evaluated for both acids. After each treatment type was held at 4°C for 0, 1, 5, and 7 days, respectively, cumulative bacterial counts were evaluated. The quantity of surviving coliforms and Escherichia coli on lettuce was decreased by roughly 2-3 log 10 cfu/g (p 0.05) as the hypochlorite acids concentration is higher, compared to just about 1 log 10 cfu/g decrease on carrots. However, whenever the PA level is higher, the bacterium rates on carrots significantly decreased by 3-4 log 10 cfu/g (p>0.05), whereas the rates on lettuce leaves have only been lowered. The highest summation squared errors for remaining coliforms and E. coli via neural predictions were 0.40 and 0.64, correspondingly, while the highest regression analysis for remnant coliforms and E. coli was 0.95 and 0.82, including both. |
---|---|
Bibliography: | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
ISSN: | 1687-8434 1687-8442 |
DOI: | 10.1155/2022/9793790 |