English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Agricultural image recognition tasks are becoming increasingly dependent ondeep learning (DL); however, despite the excellent performance of DL, it isdifficult to comprehend the type of logic or features of the input image ituses during decision making. Knowing the logic or features is highly crucialfor result verification, algorithm improvement, training data improvement, andknowledge extraction. However, the explanations from the current heatmap-basedalgorithms are insufficient for the abovementioned requirements. To addressthis, this paper details the development of a classification and explanationmethod based on a variational autoencoder (VAE) architecture, which canvisualize the variations of the most important features by visualizing thegenerated images that correspond to the variations of those features. Using thePlantVillage dataset, an acceptable level of explainability was achievedwithout sacrificing the classification accuracy. The proposed method can alsobe extended to other crops as well as other image classification tasks.Further, application systems using this method for disease identificationtasks, such as the identification of potato blackleg disease, potato virus Y,and other image classification tasks, are currently being developed.

Achieving Explainability for Plant Disease Classification with Disentangled Variational Autoencoders