ORIGINAL RESEARCH article
Front. Plant Sci.
Sec. Sustainable and Intelligent Phytoprotection
Volume 16 - 2025 | doi: 10.3389/fpls.2025.1671755
This article is part of the Research TopicAI-Driven Plant Intelligence: Bridging Multimodal Sensing, Adaptive Learning, and Ecological Sustainability in Precision Plant ProtectionView all 4 articles
Cotton Pest and Disease Diagnosis via YOLOv11-Based Deep Learning and Knowledge Graphs: A Real-Time Voice-Enabled Edge Solution
Provisionally accepted
- Gansu Agricultural University, Lanzhou, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
To address high labor costs, expert shortages, and slow response times in cotton pest and disease management, this paper presents an intelligent system that integrates deep learning– based object detection, a domain-specific knowledge graph, and real-time voice interaction. We construct a comprehensive knowledge graph with over 3,000 triples across seven major cotton pest and disease categories by fusing expert-curated and web-sourced knowledge. For image-based recognition, we develop an enhanced YOLOv11 model with LAMP pruning and a teacher–assistant–student distillation strategy, enabling lightweight, high-performance deployment on Jetson Xavier NX. The optimized model (0.3M parameters) attains mAP50=0.835 at 52 FPS. Detected results are semantically matched to the knowledge graph to provide context-aware, actionable recommendations, which are delivered via Bluetooth-based voice feedback to support accessible, efficient field management for non-expert users.
Keywords: Cotton pest and disease detection, object detection, knowledge graph, Voice interaction, Model pruning, Knowledgedistillation
Received: 23 Jul 2025; Accepted: 18 Sep 2025.
Copyright: © 2025 Zhong, Wei and Mo. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Linjing Wei, wlj@gsau.edu.cn
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.