HRL-ViT: Human–Robot Collaborative Vision Transformer for AIoT-Enabled Leaf Disease Detection in Precision Agriculture
Bibliographic record
Abstract
The combination of artificial intelligence and Internet of Things (AIoT) technologies is changing precision agriculture by making it possible to automatically check the health of crops. Early detection of leaf diseases is still important for stopping yield losses, but regular convolutional neural networks (CNNs) often don't work as well when they have to deal with different textures, lighting changes, and noise on the field level. To address these constraints, this study presents HRL-ViT, a Human–Robot Collaborative Learning framework that utilizes Vision Transformers for leaf disease identification. The frame-work merges the global attention feature of Vision Transformers with a human-in-the-loop approach, wherein predictions with low confidence are validated by experts and used to improve the model over time. The system is also made for edge-based AIoT deployment, which lets you analyze data in real time in agricultural settings. Experimental research utilizing both benchmark datasets and field-acquired images demonstrates that HRL-ViT consistently surpasses baseline CNN and Transformer models, attaining superior accuracy, precision, and recall while minimizing false detections. Transformers' attention maps can be visualized to make them even easier to understand, which helps users trust them and make decisions. In general, HRL-ViT shows a lot of promise for use in autonomous robotic platforms. It offers an explainable and scalable way to find diseases in precision agriculture.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".