Knowledge graph and deep learning based pest detection and identification system for fruit quality
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Fruit usually plays a vital role in people's daily life. Many kinds of fruits are rich in vitamins and trace elements, which have high edible value. Pests and diseases are a considerable problem in the process of fruit planting. The quality and quantity of fruit can be effectively improved by the detection and preventing pests and diseases. However, suppose in the process of fruit growth, it is always necessary to manually identify and detect pests and diseases. In that case, it will inevitably consume a lot of workforce and material resources. Therefore, it is advisable to have an automated system to save unnecessary time and effort. This article introduces the detection and identification system of pests and diseases based on Raspberry Pi to identify and detect the pests and diseases of fruit such as Longan and lychee. Firstly, we constructed a knowledge graph of pests and diseases related to lychee and longan. Then, we used the Raspberry Pi to control the camera to capture the pests and diseases images. Next, the system processed and recognized the images captured by the camera. Finally, the Bluetooth speaker broadcasted the results in realtime. We constructed the knowledge graph through data collection, information extraction, knowledge fusion and storage. We trained the vgg-16 model, which achieves 94.9% accuracy in the pests identification task, and we deployed it on a Raspberry Pi.
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.
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 | 0.000 | 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 it