Research on Optimizing Electronic Nose Sensor Arrays for Oyster Cold Chain Detection Based on Multi-Algorithm...

Area of Science:

• Food Science
• Sensor Technology
• Data Science

Background:

• Real-time quality monitoring is crucial for food safety in oyster cold chain transportation.
• Existing electronic nose systems face challenges with redundancy and environmental adaptability.
• Optimizing sensor arrays is key to improving monitoring system performance.

Purpose of the Study:

• To develop a multi-algorithm collaborative optimization strategy for electronic nose sensor array optimization.
• To enhance environmental adaptability and reduce redundancy in sensor systems for cold chain monitoring.
• To provide an intelligent, high-precision technical solution for oyster cold chain quality control.

Main Methods:

• Integrated ten gas sensors (TGS and MQ series).
• Employed Random Forest (RFA), Simulated Annealing (SA), and Genetic Quantum Particle Swarm Optimization (GA-QPSO) for sensor selection.
• Validated optimization using K-nearest neighbors (KNN) and K-means clustering under various temperatures (4°C, 12°C, 20°C, 28°C).

Main Results:

• Reduced optimized sensor count from 10 to 5-6 units.
• Maintained recognition accuracy above 95%.
• Decreased sensor redundancy by over 40%.

Conclusions:

• The multi-algorithm collaborative optimization effectively balances recognition precision, resource efficiency, and environmental adaptability.
• The proposed system offers an intelligent and high-precision solution for oyster cold chain monitoring.
• This approach significantly improves the performance of electronic nose systems in dynamic cold chain environments.