Automatic detection and diagnosis of cocoa diseases using mobile tech and deep learning
Bibliographic record
Abstract
Cocoa is a cash crop that contributes about 3% to the gross domestic product (GDP) of Ghana's economy and makes up about 20% of total export receipts according to the Ghana statistical service. However, revenue has been hampered recently by the outbreak of cocoa diseases such as Swollen shoot and black pod thereby causing up to 11% loss of the crop. There is, therefore, a need for urgent intervention by all stakeholders within the cocoa production sector. In this research, we aim to employ mobile technology and machine learning (ML) techniques to enhance the early detection and diagnosis of the two major diseases that affect cocoa production namely - swollen shoot and black pod. Specifically, a distributed mobile application is developed that enables farmers to take a picture or video of the cocoa and the app will analyse and automatically detect the specific disease. The app consequently suggests the best treatment to undertake using an inbuilt-information guide. The automatic detection and diagnosis of diseases are based on deep convolutional neural networks (CNN) for image analysis, classification, and detection. The research analysed 2,828 cocoa images spread across three class labels. We built and trained four CNN models, namely CentreNet ResNet50 V2, EfficientDet D0, SSD MobileNet V2, and SSD ResNet50 V1 FPN. We found the best generalised and fastest model to be the SSD MobileNet V2 with a detection confidence score of approximately 88.0%.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".