Towards improving prediction accuracy and user-level explainability using deep learning and knowledge graphs: a study on cassava disease
Towards improving prediction accuracy and user-level explainability using deep learning and knowledge graphs: a study on cassava disease
Food security is currently a major concern due to the growing global population, the exponential increase in food demand, the deterioration of soil quality, the occurrence of numerous diseases, and the effects of climate change on crop yield. Sustainable agriculture is necessary to solve this food security challenge. Disruptive technologies, such as of artificial intelligence, especially, deep learning techniques can contribute to agricultural sustainability. For example, applying deep learning techniques for early disease classification allows us to take timely action, thereby helping to increase the yield without inflicting unnecessary environmental damage, such as excessive use of fertilisers or pesticides. Several studies have been conducted on agricultural sustainability using deep learning techniques and also semantic web technologies such as ontologies and knowledge graphs. However, the three major challenges remain: (i) the lack of explainability of deep learning-based systems (e.g. disease information), especially to non-experts like farmers; (ii) a lack of contextual information (e.g. soil or plant information) and domain-expert knowledge in deep learning-based systems; and (iii) the lack of pattern learning ability of systems based on the semantic web, despite their ability to incorporate domain knowledge. Therefore, this paper presents the work on disease classification, addressing the challenges as mentioned earlier by combining deep learning and semantic web technologies, namely ontologies and knowledge graphs. The findings are: (i) 0.905 (90.5%) prediction accuracy on large noisy dataset; (ii) ability to generate user-level explanations about disease and incorporate contextual and domain knowledge; (iii) the average prediction latency of 3.8514 s on 5268 samples; (iv) 95% of users finding the explanation of the proposed method useful; and (v) 85% of users being able to understand generated explanations easily—show that the proposed method is superior to the state-of-the-art in terms of performance and explainability and is also suitable for real-world scenarios.
Agricultural sustainability, Cassava, Deep learning, Explainable AI (XAI), Knowledge graphs
Chhetri, Tek Raj
c3431de5-4860-43e5-b09f-3dbb752c8490
Hohenegger, Armin
fa74c318-9dae-4af8-8493-4b6446a99f00
Fensel, Anna
6d0be8a7-8261-48f1-9214-fc5fc59c40d3
Kasali, Mariam Aramide
210239ac-7848-4380-9c53-d4565a84add7
Adekunle, Asiru Afeez
c466ad02-d135-4f4e-99c0-c9b677ccf9eb
15 December 2023
Chhetri, Tek Raj
c3431de5-4860-43e5-b09f-3dbb752c8490
Hohenegger, Armin
fa74c318-9dae-4af8-8493-4b6446a99f00
Fensel, Anna
6d0be8a7-8261-48f1-9214-fc5fc59c40d3
Kasali, Mariam Aramide
210239ac-7848-4380-9c53-d4565a84add7
Adekunle, Asiru Afeez
c466ad02-d135-4f4e-99c0-c9b677ccf9eb
Chhetri, Tek Raj, Hohenegger, Armin, Fensel, Anna, Kasali, Mariam Aramide and Adekunle, Asiru Afeez
(2023)
Towards improving prediction accuracy and user-level explainability using deep learning and knowledge graphs: a study on cassava disease.
Expert Systems with Applications, 233, [120955].
(doi:10.1016/j.eswa.2023.120955).
Abstract
Food security is currently a major concern due to the growing global population, the exponential increase in food demand, the deterioration of soil quality, the occurrence of numerous diseases, and the effects of climate change on crop yield. Sustainable agriculture is necessary to solve this food security challenge. Disruptive technologies, such as of artificial intelligence, especially, deep learning techniques can contribute to agricultural sustainability. For example, applying deep learning techniques for early disease classification allows us to take timely action, thereby helping to increase the yield without inflicting unnecessary environmental damage, such as excessive use of fertilisers or pesticides. Several studies have been conducted on agricultural sustainability using deep learning techniques and also semantic web technologies such as ontologies and knowledge graphs. However, the three major challenges remain: (i) the lack of explainability of deep learning-based systems (e.g. disease information), especially to non-experts like farmers; (ii) a lack of contextual information (e.g. soil or plant information) and domain-expert knowledge in deep learning-based systems; and (iii) the lack of pattern learning ability of systems based on the semantic web, despite their ability to incorporate domain knowledge. Therefore, this paper presents the work on disease classification, addressing the challenges as mentioned earlier by combining deep learning and semantic web technologies, namely ontologies and knowledge graphs. The findings are: (i) 0.905 (90.5%) prediction accuracy on large noisy dataset; (ii) ability to generate user-level explanations about disease and incorporate contextual and domain knowledge; (iii) the average prediction latency of 3.8514 s on 5268 samples; (iv) 95% of users finding the explanation of the proposed method useful; and (v) 85% of users being able to understand generated explanations easily—show that the proposed method is superior to the state-of-the-art in terms of performance and explainability and is also suitable for real-world scenarios.
Text
1-s2.0-S0957417423014574-main
- Version of Record
More information
Accepted/In Press date: 5 July 2023
e-pub ahead of print date: 8 July 2023
Published date: 15 December 2023
Additional Information:
Funding Information:
This research is partially supported by Interreg Österreich-Bayern 2014–2020 programme project KI-Net : Bausteine für KI-basierte Optimierungen in der industriellen Fertigung (grant agreement : AB 292 ). We would like thank to the High-Performance Computing Centre (HPC) at the University of Innsbruck for providing the LEO HPC infrastructure for our experiment. We also want to express our gratitude to Michael Fink, a member of the HPC staff, for his assistance with HPC administrative tasks and for accelerating the procedure to reduce delay. In addition, we would like to thank everyone who participated in our survey and gave us permission to analyse and utilise their responses in our research.
Funding Information:
This research is partially supported by Interreg Österreich-Bayern 2014–2020 programme project KI-Net: Bausteine für KI-basierte Optimierungen in der industriellen Fertigung (grant agreement : AB 292). We would like thank to the High-Performance Computing Centre (HPC) at the University of Innsbruck for providing the LEO HPC infrastructure for our experiment. We also want to express our gratitude to Michael Fink, a member of the HPC staff, for his assistance with HPC administrative tasks and for accelerating the procedure to reduce delay. In addition, we would like to thank everyone who participated in our survey and gave us permission to analyse and utilise their responses in our research.
Publisher Copyright:
© 2023 The Author(s)
Keywords:
Agricultural sustainability, Cassava, Deep learning, Explainable AI (XAI), Knowledge graphs
Identifiers
Local EPrints ID: 481448
URI: http://eprints.soton.ac.uk/id/eprint/481448
ISSN: 0957-4174
PURE UUID: 239152f5-7fdb-4b82-9139-64b30d963ea9
Catalogue record
Date deposited: 29 Aug 2023 16:49
Last modified: 05 Jun 2024 18:00
Export record
Altmetrics
Contributors
Author:
Tek Raj Chhetri
Author:
Armin Hohenegger
Author:
Anna Fensel
Author:
Mariam Aramide Kasali
Author:
Asiru Afeez Adekunle
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics