Cargando…

Pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection

Frequency is essential in signal transmission, especially in convolutional neural networks. It is vital to maintain the signal frequency in the neural network to maintain the performance of a convolutional neural network. Due to destructive signal transmission in convolutional neural network, signal...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Jiayu, Qi, Chao, Mecha, Peter, Zuo, Yi, Ben, Zongyou, Liu, Haolu, Chen, Kunjie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9749340/
https://www.ncbi.nlm.nih.gov/pubmed/36517873
http://dx.doi.org/10.1186/s13007-022-00969-w
_version_ 1784850020074258432
author Zhang, Jiayu
Qi, Chao
Mecha, Peter
Zuo, Yi
Ben, Zongyou
Liu, Haolu
Chen, Kunjie
author_facet Zhang, Jiayu
Qi, Chao
Mecha, Peter
Zuo, Yi
Ben, Zongyou
Liu, Haolu
Chen, Kunjie
author_sort Zhang, Jiayu
collection PubMed
description Frequency is essential in signal transmission, especially in convolutional neural networks. It is vital to maintain the signal frequency in the neural network to maintain the performance of a convolutional neural network. Due to destructive signal transmission in convolutional neural network, signal frequency downconversion in channels results into incomplete spatial information. In communication theory, the number of Fourier series coefficients determines the integrity of the information transmitted in channels. Consequently, the number of Fourier series coefficients of the signals can be replenished to reduce the information transmission loss. To achieve this, the ArsenicNetPlus neural network was proposed for signal transmission modulation in detecting cassava diseases. First, multiattention was used to maintain the long-term dependency of the features of cassava diseases. Afterward, depthwise convolution was implemented to remove aliasing signals and downconvert before the sampling operation. Instance batch normalization algorithm was utilized to keep features in an appropriate form in the convolutional neural network channels. Finally, the ArsenicPlus block was implemented to generate pseudo high-frequency in the residual structure. The proposed method was tested on the Cassava Datasets and compared with the V2-ResNet-101, EfficientNet-B5, RepVGG-B3g4 and AlexNet. The results showed that the proposed method performed [Formula: see text] in terms of accuracy, 1.2440 in terms of loss, and [Formula: see text] in terms of the F1-score, outperforming the comparison algorithms.
format Online
Article
Text
id pubmed-9749340
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher BioMed Central
record_format MEDLINE/PubMed
spelling pubmed-97493402022-12-15 Pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection Zhang, Jiayu Qi, Chao Mecha, Peter Zuo, Yi Ben, Zongyou Liu, Haolu Chen, Kunjie Plant Methods Research Frequency is essential in signal transmission, especially in convolutional neural networks. It is vital to maintain the signal frequency in the neural network to maintain the performance of a convolutional neural network. Due to destructive signal transmission in convolutional neural network, signal frequency downconversion in channels results into incomplete spatial information. In communication theory, the number of Fourier series coefficients determines the integrity of the information transmitted in channels. Consequently, the number of Fourier series coefficients of the signals can be replenished to reduce the information transmission loss. To achieve this, the ArsenicNetPlus neural network was proposed for signal transmission modulation in detecting cassava diseases. First, multiattention was used to maintain the long-term dependency of the features of cassava diseases. Afterward, depthwise convolution was implemented to remove aliasing signals and downconvert before the sampling operation. Instance batch normalization algorithm was utilized to keep features in an appropriate form in the convolutional neural network channels. Finally, the ArsenicPlus block was implemented to generate pseudo high-frequency in the residual structure. The proposed method was tested on the Cassava Datasets and compared with the V2-ResNet-101, EfficientNet-B5, RepVGG-B3g4 and AlexNet. The results showed that the proposed method performed [Formula: see text] in terms of accuracy, 1.2440 in terms of loss, and [Formula: see text] in terms of the F1-score, outperforming the comparison algorithms. BioMed Central 2022-12-14 /pmc/articles/PMC9749340/ /pubmed/36517873 http://dx.doi.org/10.1186/s13007-022-00969-w Text en © The Author(s) 2022 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/ (https://creativecommons.org/publicdomain/zero/1.0/) ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.
spellingShingle Research
Zhang, Jiayu
Qi, Chao
Mecha, Peter
Zuo, Yi
Ben, Zongyou
Liu, Haolu
Chen, Kunjie
Pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection
title Pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection
title_full Pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection
title_fullStr Pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection
title_full_unstemmed Pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection
title_short Pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection
title_sort pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection
topic Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9749340/
https://www.ncbi.nlm.nih.gov/pubmed/36517873
http://dx.doi.org/10.1186/s13007-022-00969-w
work_keys_str_mv AT zhangjiayu pseudohighfrequencybooststhegeneralizationofaconvolutionalneuralnetworkforcassavadiseasedetection
AT qichao pseudohighfrequencybooststhegeneralizationofaconvolutionalneuralnetworkforcassavadiseasedetection
AT mechapeter pseudohighfrequencybooststhegeneralizationofaconvolutionalneuralnetworkforcassavadiseasedetection
AT zuoyi pseudohighfrequencybooststhegeneralizationofaconvolutionalneuralnetworkforcassavadiseasedetection
AT benzongyou pseudohighfrequencybooststhegeneralizationofaconvolutionalneuralnetworkforcassavadiseasedetection
AT liuhaolu pseudohighfrequencybooststhegeneralizationofaconvolutionalneuralnetworkforcassavadiseasedetection
AT chenkunjie pseudohighfrequencybooststhegeneralizationofaconvolutionalneuralnetworkforcassavadiseasedetection