Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Aug 28;12(9):692.
doi: 10.3390/bios12090692.

An Apple Fungal Infection Detection Model Based on BPNN Optimized by Sparrow Search Algorithm

Changtong Zhao  1 , Jie Ma  1 , Wenshen Jia  1   2 , Huihua Wang  3 , Hui Tian  1 , Jihua Wang  2 , Wei Zhou  4
Affiliations

An Apple Fungal Infection Detection Model Based on BPNN Optimized by Sparrow Search Algorithm

Changtong Zhao et al. Biosensors (Basel). .

Abstract

To rapidly detect whether apples are infected by fungi, a portable electronic nose was used in this study to collect the gas information from apples, and the collected information was processed by smoothing filtering, data dimensionality reduction, and outlier removal. Following this, we utilized K-nearest neighbors (KNN), random forest (RF), support vector machine (SVM), a convolutional neural network (CNN), a back-propagation neural network (BPNN), a particle swarm optimization-back-propagation neural network (PSO-BPNN), a gray wolf optimization-backward propagation neural network (GWO-BPNN), and a sparrow search algorithm-backward propagation neural network (SSA-BPNN) model to discriminate apple samples, and adopted the 10-fold cross-validation method to evaluate the performance of each model. The results show that SSA can effectively optimize the performance of the BPNN, such that the recognition accuracy of the optimized SSA-BPNN model reaches 98.40%. This study provides an important reference value for the application of an electronic nose in the non-destructive and rapid detection of fungal infection in apples.

Keywords: apples; electronic nose; fungal infection; sparrow search algorithm.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
(a) The portable electronic nose; (b) schematic diagram of the portable electronic nose.
Figure 2
Figure 2
The response curve of the No. 1 sensor C2H4-20 during the entire sample-collection period. When opening the injection and vacuum valve at 50 s, the collection time lasts 350 s, and the purging of the electronic nose lasts 500 s.
Figure 3
Figure 3
(a) Original response curve. (b) Response curve after 3-point smoothing filtering. (c) Response curve after 5-point smoothing filtering. (d) Response curve after 7-point smoothing filtering. (e) Response curve after 9-point smoothing filtering. (f) Response curve after 11-point smoothing filtering.
Figure 4
Figure 4
Comparison of different data dimensionality reduction methods: (a) PCA dimensionality reduction analysis; (b) FA dimensionality reduction analysis; (c) LDA dimensionality reduction analysis.
Figure 5
Figure 5
Schematic diagram of the sparrow search algorithm.
Figure 6
Figure 6
Multi-algorithm pattern recognition model platform. (a) Main interface of multi-algorithm pattern recognition platform. (b) KNN pattern recognition interface. (c) CNN pattern recognition interface. (d) SVM pattern recognition interface. (e) RF pattern recognition model interface. (f) BPNN pattern recognition model interface. (g) PSO-BPNN pattern recognition interface. (h) GWO-BPNN pattern recognition interface. (i) SSA-BPNN pattern recognition interface. (j) SSA-BPNN detection sample interface.
Figure 6
Figure 6
Multi-algorithm pattern recognition model platform. (a) Main interface of multi-algorithm pattern recognition platform. (b) KNN pattern recognition interface. (c) CNN pattern recognition interface. (d) SVM pattern recognition interface. (e) RF pattern recognition model interface. (f) BPNN pattern recognition model interface. (g) PSO-BPNN pattern recognition interface. (h) GWO-BPNN pattern recognition interface. (i) SSA-BPNN pattern recognition interface. (j) SSA-BPNN detection sample interface.
Figure 7
Figure 7
Variation trend of the fitness function curves of SSA, GWO, and PSO with the number of iterations. The SSA-BPNN model reached the optimal state first.
See this image and copyright information in PMC

References

    1. Kang N.J., Lee K.W., Lee S.J., Lee C.Y., Lee H.J. Effects of phenolics in Empire apples on hydrogen peroxide-induced inhibition of gap-junctional intercellular communication. Biofactors. 2004;21:361–365. doi: 10.1002/biof.552210169. - DOI - PubMed
    1. Munir N., Rafique M., Altaf I., Sharif N., Naz S. Antioxidant and antimicrobial activities of extracts from selected algal species. Bangladesh J. Bot. 2018;47:53–61.
    1. Guo Z., Wang M., Barimah A.O., Chen Q., Li H., Shi J., El-Seedi H.R., Zou X. Label-free surface enhanced Raman scattering spectroscopy for discrimination and detection of dominant apple spoilage fungus. Int. J. Food Microbiol. 2020;338:108990. doi: 10.1016/j.ijfoodmicro.2020.108990. - DOI - PubMed
    1. Žebeljan A., Vico I., Duduk N., Žiberna B., Krajnc A.U. Profiling changes in primary metabolites and antioxidants during apple fruit decay caused by Penicillium crustosum. Physiol. Mol. Plant Pathol. 2020;113:101586. doi: 10.1016/j.pmpp.2020.101586. - DOI
    1. Berrada H., Buys E., Mañes J., Font G. Determination of patulin in apple juice by GC–MS/MS: Stability study during storage. Toxicol. Lett. 2012;211:S97. doi: 10.1016/j.toxlet.2012.03.366. - DOI