Towards improving prediction accuracy and user-level explainability using deep learning and knowledge graphs: A study on cassava disease

Chhetri, Tek Raj; Hohenegger, Armin; Fensel, Anna; Kasali, Mariam Aramide; Adekunle, Asiru Afeez

doi:10.1016/j.eswa.2023.120955

Cited by 11 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In practical applications, the use of knowledge graphs helps the model to better understand the characteristics of cotton pests and diseases. For example, through the knowledge graph, the model can learn about the typical environmental conditions under which a certain pest or disease occurs, its characteristic symptoms, and how to distinguish similar pests and diseases [31][32][33]. This information is crucial for improving the model's accuracy in complex scenarios.…”

Section: Knowledge Graph In Cotton Pest and Disease Recognitionmentioning

confidence: 99%

Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge Graphs

Gao,

Dong,

Wang

et al. 2024

Agriculture

View full text Add to dashboard Cite

In this study, a deep-learning-based intelligent detection model was designed and implemented to rapidly detect cotton pests and diseases. The model integrates cutting-edge Transformer technology and knowledge graphs, effectively enhancing pest and disease feature recognition precision. With the application of edge computing technology, efficient data processing and inference analysis on mobile platforms are facilitated. Experimental results indicate that the proposed method achieved an accuracy rate of 0.94, a mean average precision (mAP) of 0.95, and frames per second (FPS) of 49.7. Compared with existing advanced models such as YOLOv8 and RetinaNet, improvements in accuracy range from 3% to 13% and in mAP from 4% to 14%, and a significant increase in processing speed was noted, ensuring rapid response capability in practical applications. Future research directions are committed to expanding the diversity and scale of datasets, optimizing the efficiency of computing resource utilization and enhancing the inference speed of the model across various devices. Furthermore, integrating environmental sensor data, such as temperature and humidity, is being considered to construct a more comprehensive and precise intelligent pest and disease detection system.

show abstract

Section: Knowledge Graph In Cotton Pest and Disease Recognitionmentioning

confidence: 99%

Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge Graphs

Gao,

Dong,

Wang

et al. 2024

Agriculture

View full text Add to dashboard Cite

show abstract

“…Moreover, inaccurate or highly biased domain knowledge can also act as a bottleneck. Therefore, even though Chhetri et al [68] recommend the incorporation of domain knowledge in the models, it should be done with extreme caution, and multiple domain experts should be involved to eliminate or reduce bias.…”

Section: -2-ethical Considerationsmentioning

confidence: 99%

“…Key dimensions of responsible innovation include anticipation, inclusion, reflexivity, and responsiveness. For instance, Chhetri et al [68] employ the microservices architecture to deploy the vision model, semantic model, and decision engine for the reusability of cassava disease classification. The BentoML and the semantic classifier REST (REpresentational State Transfer) Service were utilized for this purpose.…”

Section: -3-collaboration and Responsible Innovationmentioning

confidence: 99%

Agriculture 5.0 and Explainable AI for Smart Agriculture: A Scoping Review

Abdul Razak,

Yogarayan,

Sayeed

et al. 2024

Emerg Sci J

View full text Add to dashboard Cite

The visionary paradigm of Agriculture 5.0 integrates Industry 4.0 principles into agricultural practices. Our scoping review explores the landscape of Agriculture 5.0, emphasizing the pivotal role of Explainable AI (XAI) in shaping this domain. Guided by the Preferred Reporting Items for Systematic Review and Meta-Analysis Scoping Review, we rigorously analyzed 84 articles published from 2018 to September 2023. Our findings highlight XAI’s potential within Agriculture 5.0, recognizing its influence on intelligent farming. We propose a conceptual framework for integrating XAI, emphasizing its impact on model transparency and user trust. Despite transformative applications, existing literature often lacks XAI discussions. Our objective is to bridge this gap and provide a reference for academics, practitioners, policymakers, and educators in the field of smart agriculture that is both environmentally friendly and technologically advanced. Doi: 10.28991/ESJ-2024-08-02-024 Full Text: PDF

show abstract

Integrating Domain Knowledge for Enhanced Concept Model Explainability in Plant Disease Classification

Amara,

Samuel,

König-Ries

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Towards improving prediction accuracy and user-level explainability using deep learning and knowledge graphs: A study on cassava disease

Cited by 11 publications

References 43 publications

Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge Graphs

Intelligent Cotton Pest and Disease Detection: Edge Computing Solutions with Transformer Technology and Knowledge Graphs

Agriculture 5.0 and Explainable AI for Smart Agriculture: A Scoping Review

Integrating Domain Knowledge for Enhanced Concept Model Explainability in Plant Disease Classification

Contact Info

Product

Resources

About