Agricultural Harvester Sound Classification using Convolutional Neural Networks and Spectrograms
Bibliographic record
Abstract
Highlights Automatic classification of harvester sounds. Final classification obtained using three convolutional neural networks. The results of the networks were combined via stacking and voting to achieve 100% accuracy. Abstract. The use of deep learning in agricultural tasks has recently become popular. Deep learning networks have been used for analyzing images of crops, identifying paddy areas, distinguishing sick plants from healthy ones, to name a few applications. Besides visual systems, sound analysis of agricultural machinery is a time-sensitive task that can also be incorporated in decision making and can be done with the help of deep learning models. We propose a method to generate spectrogram images from the sound of a harvester and classify them into three working modes in real-time. We used three convolutional neural networks and use the outputs of these networks as inputs to a stacking ensemble method to improve the accuracy of the system. To achieve 100% classification accuracy, a final decision is made by voting based on several consecutive classifications made by the stacking step. We were able to perform classifications in less than 1 s which was the standard to be considered as a safe time for the harvester. Keywords: Convolutional neural networks, Deep learning, Spectrograms, Stacking, Voting.
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) | 0.000 | 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 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".