A Hybrid Plant Disease Detection Algorithm Using Residual MBi-LSTM With CNN Model
Bibliographic record
Abstract
In India, various plant diseases affect agricultural productivity. For this reason, crop losses occur every year. On-time, the accurate detection of all diseases is essential to ensure healthy plants and can lead to improved yields. Traditionally, we needed the expertise of an agricultural specialist. However, in recent years, numerous deep-learning methods have been introduced, promising to automate the diagnosis of plant diseases using the images of infected plants. Despite these achievements, many existing models fail to function effectively when data are altered according to time and place. To address this problem, we propose a model that combines VGG16 with a multilayer bidirectional long short-term memory (MBi-LSTM) network. The VGG16 component captures spatial hierarchies and extracts features in the images. The MBi-LSTM layers learn temporal relationships across image sequences. By integrating both spatial and temporal information, our hybrid approach achieves a deeper understanding of visual patterns as compared to models that rely solely on spatial features. We use two datasets (PlantVillage and real world) for training and testing our proposed model of labeled plant disease images. Quantitative results demonstrate that, across all evaluation metrics—accuracy, precision, recall, andF1-score—the VGG16 + MBi-LSTM model achieved the highest performance. The classification accuracy achieved by the model on the PlantVillage dataset is 98.9% and on the real-world dataset is 96.6%, showcasing its effectiveness for real-time disease detection. This method provides a reliable solution for disease prediction, enabling farmers to take preventive measures at an early stage of the crop’s development.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| 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".