Detection of damaged seeds in laboratory evaluation of precision planter using impact acoustics and artificial neural networks
Bibliographic record
Abstract
In the present study, feasibility of laboratory detection of damaged seeds in precision planters caused by malfunction of seed metering device was investigated. An acoustic-based intelligent system was developed for detection of damaged pelleted tomato seeds. To improve the Artificial Neural Network (ANN) models a total of 2000 seeds sound signals, 1000 samples for damaged seeds and 1000 for undamaged ones were recorded. When seed metering device drove out seeds, the ejected seeds were impacted to steel plate, and their acoustic signals were recorded from the impact. The bounced seeds lied on the running grease belt. In each stage of experiments, damaged seeds were determined manually in grease belt and related damaged seed sound signals were designated. Achieved acoustic signals, were processed and potential features were extracted from the analysis of sound signals in time and frequency domains. The method is based on feature generation by Fast Fourier Transform (FFT), feature selection by statistical methods and classification by Multilayer Feed forward Neural Network. Features such as amplitude, phase and power spectrum of sound signals were computed through a 1024-point FFT. By using statistical factors (maximum, minimum, median, mean and variance) for each vector of data, feature vector was reduced to 15 factors. In developing the ANN models, several ANN architectures, each having different numbers of neurons in hidden layer, were evaluated. The best model was chosen after a number of evaluations based on minimizing the mean square error (MSE), correct detection rate (CDR) and correlation coefficient (r). Selected ANN, 15-17-2 was configured for classification. CDR of the proposed ANN model for undamaged and damaged seeds was 99.49 and 100 respectively. MSE of the system was found to be 0.0109.
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) | 0.000 | 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 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".