Development of a Web and Mobile Applications-Based Cassava Disease Classification Interface Using Convolutional Neural Network
Bibliographic record
Abstract
Cassava is one of the six food items identified as a critical food product for Africa, owing to its importance to African farmers' lives and ability to alter African economies. However, Cassava plant diseases have affected the yield of farmers significantly which has led to a decline in the agricultural production of cassava. Therefore, the aim of this research work is to develop a web and mobile applications-based system that would be able to detect cassava diseases based on its leaf images. To achieve this aim, pre-trained Convolutional Neural Network (CNN) models were selected using their previous performance and the application of transfer learning technique, new models were developed to classify cassava diseases based on the dataset curated and pre-processed. The best three models were selected: MobileNetV2, VGG16 and ResNet50. After training, the accuracy for each model was: 98%, 92% and 75% for MobileNetV2, VGG16 and ResNet50 respectively. Following evaluation of performance, the model with the best accuracy (MobileNetV2) was deployed using a web application interface. After deploying as a web and mobile apps interface, it was further tested to see how it would perform on the field. This research work was found capable of aiding farmers in being able to timely detect the type of disease affecting their cassava plants and the correct treatment to utilize; this also contribute towards Sustainable development goals (SDG) 2 and 12.
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 | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.003 |
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".