Edge Computing-Based Machine Vision for Non-Invasive and Rapid Soft Sensing of Mushroom Liquid Strain Biomass
Bibliographic record
Abstract
Biomass monitoring of mushroom liquid strains during the fermentation process demands real-time analysis with minimal manual intervention, highlighting the urgent need for intelligent surveillance. This study introduced a soft sensor method based on edge computing machine vision, termed Edge CV, for in situ non-invasive estimation of biomass. In our experiment, the hardware of the Edge CV system includes the Jetson Nano with 4 GB RAM, 64 GB ROM, and a 128-core Maxwell GPU for executing intelligent machine vision tasks, along with embedded cameras for image data acquisition. Furthermore, a cascaded machine vision model was developed to enable biomass evaluation on the Edge CV system. The cascaded machine vision model mainly consists of three steps: first, the object detection task to locate the observation window, achieving a mean Average Precision (mAP50:95) of 82.3% with 78.7 GFLOPs; then, the segmentation task to extract liquid strain data within the observation window, yielding a mean intersection over union (MIoU) of 85.9% with 110.4 GFLOPs; and finally, calculating mycelium biomass indices via the morphological image processing task. The correlation between Edge CV inference and manual measurement showed an R2 of 0.963 and an RMSE of 0.027 for normalized biomass indices, demonstrating a robust and consistent trend. Therefore, this study illustrates the practical application of edge computing-based machine vision for biomass soft sensing during the fermentation process.
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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".