Assessment of fish adulteration using SnO2 nanopetal-based gas sensor and machine learning

The work presents the identification of fish adulteration and quality assessment by incorporating a chemiresistive gas sensor and machine learning (ML) techniques. Highly sensitive SnO2 nanopetals were synthesized chemically and integrated with interdigitated electrodes to fabricate a sensor device. The sensor was calibrated with formaldehyde (37 %) with a theoretical detection limit of 75 ppb and further utilized to detect the vapors emitted from fresh and formalin-adulterated fish. An extensive sensing investigation was conducted with freshly caught Rohu fish samples. The sensing behavior was examined for all the samples at different time intervals to estimate the spoilage level. The classification between fresh and adulterated fish samples was obtained with 100 % accuracy by employing ML tools. Moreover, the storage duration and spoilage level of fish samples were quantified using regression models. This work emphasizes the potential of nanomaterials combined with machine learning for the accurate detection of adulteration in food systems.

Automated summary

This work presents the use of a chemiresistive gas sensor and machine learning techniques for the identification of fish adulteration and quality assessment. A highly sensitive SnO2 nanopetal-based sensor device was fabricated and calibrated to detect formaldehyde in fish samples. The sensing behavior of the sensor was used to estimate the spoilage level of freshly caught fish samples and classify them as fresh or adulterated with 100% accuracy using machine learning tools. Additionally, regression models were used to quantify the storage duration and spoilage level of fish samples.