.png){kind=icon}
.png){kind=icon}
Return
Real-time and explainable non-destructive nut classification using spike-triggered acoustic sensing
.png){kind=icon}
OA
AI
DOI：10.1016/j.compag.2026.111502.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Spike-triggered acoustic pipeline for online, non-destructive walnut classification. • Fusion of MFCC and spectral features boosts F1-scores up to 0.94. • Low-cost hardware and millisecond processing enable real-time industrial deployment. • Random Forest with post-hoc Decision Predicate Graphs (DPGs) to explain decisions.
Keywords:
Non-destructive inspection
Walnut classification
Acoustic sensing
Spectral features
Mel-Frequency Cepstral Coefficients (MFCCs)
Random Forest
On-site quality monitoring
Real-time food inspection
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
8.9
Papers:
9.9K
Citations:
4.8W