Smartphone-Assisted Aerogel Colorimetric Sensor Array Coupled with Lightweight Deep Learning for Multi-Meat Freshness Monitoring.
- 1College of Engineering, Huazhong Agricultural University, Wuhan 430070, China.
- 2Ningbo Academy of Agricultural Sciences, Ningbo 315040, China.
- 3School of Life and Health Sciences, Hubei University of Technology, Wuhan 430068, China.
Abstract
Rapid assessment of chilled-meat freshness is constrained by conventional laboratory-based measurements. Although food-detection studies emphasize predictive performance, computational cost is reported less consistently. Here, we developed a 2 × 2 colorimetric sensor array based on a porous konjac glucomannan (KGM)/gelatin/starch/SiO₂ aerogel substrate loaded with four pH-sensitive dyes. Sensor images were acquired with a smartphone under standardized conditions, and four dye-responsive regions of interest (ROIs) were manually extracted and assembled into 2 × 2 dye-grid images. Five lightweight models-Spot-CNN, ShuffleNetV2-0.5x, EfficientNet-Lite0, MobileNetV3-Small and Tiny-MLP-were evaluated for classifying beef and pork freshness as Fresh, Sub-fresh or Spoiled. During chilled storage, the sensor color responses showed broadly consistent temporal trends with total volatile basic nitrogen (TVB-N). Under the fixed group-level split, Spot-CNN achieved image-unit-level accuracies of 0.933 and 0.938 and macro-AUC values of 0.995 and 0.982 on the beef and pork test sets, respectively. Tiny-MLP contained 0.013 M parameters and required less than 0.001 G floating-point operations, demonstrating lower computational cost. These results establish a controlled-laboratory prototype integrating an aerogel colorimetric sensor array, standardized smartphone image processing and lightweight-model comparison for multi-meat freshness screening. Further validation across meat batches, smartphone devices, lighting conditions and deployment environments is required.
Related
- Deep learning-assisted digital interpretation of an anthocyanin-based colorimetric pH indicator for spoilage identification of packaged raw squid
- A sensitive colorimetric ELISA to measure allergen-specific salivary SIgA for monitoring sublingual immunity efficiency in pollinosis SLIT.
- Hydrogel microneedle patch for low-cost, colorimetric, continuous glucose monitoring
- IoT-enabled individual poultry monitoring with lightweight step-counting for health assessment
- Surfactant-Assisted Colorimetric Signal Enhancement in Paper-Based Glucose Sensing
BibTeX
@article{chen2026smartphoneassisted,
title = {{Smartphone-Assisted Aerogel Colorimetric Sensor Array Coupled with Lightweight Deep Learning for Multi-Meat Freshness Monitoring.}},
author = {Hanzhi Chen and Xiao Zhou and Caoyuan Zhang and Zengrui Wu and Bo Peng and Yingli Wang},
journal = {Gels (Basel, Switzerland)},
year = {2026},
month = oct,
doi = {10.3390/gels12100910},
url = {https://europepmc.org/article/MED/42929944},
note = {CC BY},
}
RIS
TY - JOUR
TI - Smartphone-Assisted Aerogel Colorimetric Sensor Array Coupled with Lightweight Deep Learning for Multi-Meat Freshness Monitoring.
AU - Hanzhi Chen
AU - Xiao Zhou
AU - Caoyuan Zhang
AU - Zengrui Wu
AU - Bo Peng
AU - Yingli Wang
PY - 2026
DA - 2026/10/09
JO - Gels (Basel, Switzerland)
DO - 10.3390/gels12100910
UR - https://europepmc.org/article/MED/42929944
AB - Rapid assessment of chilled-meat freshness is constrained by conventional laboratory-based measurements. Although food-detection studies emphasize predictive performance, computational cost is reported less consistently. Here, we developed a 2 × 2 colorimetric sensor array based on a porous konjac glucomannan (KGM)/gelatin/starch/SiO₂ aerogel substrate loaded with four pH-sensitive dyes. Sensor images were acquired with a smartphone under standardized conditions, and four dye-responsive regions of interest (ROIs) were manually extracted and assembled into 2 × 2 dye-grid images. Five lightweight models-Spot-CNN, ShuffleNetV2-0.5x, EfficientNet-Lite0, MobileNetV3-Small and Tiny-MLP-were evaluated for classifying beef and pork freshness as Fresh, Sub-fresh or Spoiled. During chilled storage, the sensor color responses showed broadly consistent temporal trends with total volatile basic nitrogen (TVB-N). Under the fixed group-level split, Spot-CNN achieved image-unit-level accuracies of 0.933 and 0.938 and macro-AUC values of 0.995 and 0.982 on the beef and pork test sets, respectively. Tiny-MLP contained 0.013 M parameters and required less than 0.001 G floating-point operations, demonstrating lower computational cost. These results establish a controlled-laboratory prototype integrating an aerogel colorimetric sensor array, standardized smartphone image processing and lightweight-model comparison for multi-meat freshness screening. Further validation across meat batches, smartphone devices, lighting conditions and deployment environments is required.
SN - 2310-2861
ER -