Deep Learning and Machine Learning Based Method for Crop Disease Detection and Identification Using Autoencoder and Neural Network
Bibliographic record
Abstract
Crop diseases present a major threat to agricultural output, disrupting both the quantity and quality of production.Disease diagnosis remains a challenge for farmers, primarily due to limited knowledge and the need for specialized agricultural engineering expertise.To solve these problems, a new technique named the Autoencoder Latent Space-Neural Network (ALS-NN) was introduced in this study.It combines the strengths of autoencoders and neural networks to find crop diseases.Data processing is the first step of the methodology, and then data compression into a latent space follows.This compressed data serves as the input for the neural network, facilitating efficient crop disease classification.This approach capitalizes on the autoencoder's capacity for dimensionality reduction, data compression, and encoding, which is particularly beneficial when handling high-dimensional data.The reduced data dimensionality enables the neural network to process the information more efficiently.The ALS-NN model, by compressing data, focuses on the crucial information for the classification process, thereby enhancing computational speed and reducing the number of trained parameters.This results in time efficiencies during disease detection operations, mitigating the detrimental effects of diseases on crop yields.The integration of autoencoders and neural networks forms a potent strategy for disease detection, leveraging the autoencoders' capabilities for dimensionality reduction, anomaly detection, and feature learning, coupled with the classification and generalization abilities of neural networks.This hybrid approach can potentially lead to more precise, efficient, and interpretable disease detection system.PlantVillage is used with 10 crop types.We used the first part of autoencoder (The encoder) to compress images into Latent space; for classification, the result is subsequently fed into a neural network.Our model (ALS-NN) achieved 90% for test accuracy and 90% for validation accuracy.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".