Blind Storage-Day Identification of Cherry Tomatoes Using a Nonlinear Electronic-Nose Sensor Response Signature Framework

Nurgül Senyücel

Blind Storage-Day Identification of Cherry Tomatoes Using a Nonlinear Electronic-Nose Sensor Response Signature Framework

Authors

Nurgül Senyücel

Dr

Author

Keywords:

Array, Array, Array

Abstract

Accurate and non-destructive determination of fruit storage status is essential for intelligent postharvest quality management. Although electronic noses have been extensively applied to freshness evaluation, most existing approaches classify raw temporal sensor signals directly or rely on manually selected features, limiting interpretability and robustness for previously unseen samples. This study proposes a nonlinear Sensor Response Signature (SRS) framework for blind storage-day identification of grapes using complete electronic-nose response curves. Four metal-oxide semiconductor sensors recorded 100-s temporal responses from grapes collected from three independent producers over seven storage days. Logistic, Gompertz, and Richards models were evaluated to characterize the sensor dynamics, and the Richards model consistently achieved the best performance (RMSE = 2.451, R² = 0.999744) with the lowest AIC, AICc, and BIC values. The fitted nonlinear parameters extracted from the four sensors were integrated into multidimensional SRSs to construct a reference signature library. Blind identification was then performed by matching independent test samples to the reference signatures without classifier retraining. Evaluation using 21 completely independent blind samples achieved an exact storage-day identification accuracy of 85.71%, while all samples were identified within ±1 day (100%), with a mean absolute error of 0.143 day and a maximum error of only one day. Compared with a conventional Support Vector Machine benchmark, the proposed framework produced higher identification accuracy and lower chronological prediction error. These results demonstrate that nonlinear Sensor Response Signatures provide an interpretable, transferable, and robust representation of grape storage progression, offering a promising strategy for practical electronic-nose-based postharvest quality monitoring.

References

Sanislav, T., Mois, G. D., Zeadally, S., Folea, S., Radoni, T. C., & Al-Suhaimi, E. A. (2025). A comprehensive review on sensor-based electronic nose for food quality and safety. Sensors, 25(14), Article 4437. https://doi.org/10.3390/s25144437

Vadera, N., & Dhanekar, S. (2025). Classification and prediction of VOCs using an IoT-enabled electronic nose system-based lab prototype for breath sensing applications. ACS Sensors, 10(1), 439–447. https://doi.org/10.1021/acssensors.4c02731

Wang, B., Li, Y., Liu, K., Wei, G., He, A., Kong, W., & Zhang, X. (2024). Intelligent evaluation and dynamic prediction of oysters freshness with electronic nose non-destructive monitoring and machine learning. Biosensors, 14(10), Article 502. https://doi.org/10.3390/bios14100502

Zhai, Z., Liu, Y., Li, C., Wang, D., & Wu, H. (2024). Electronic noses: From gas-sensitive components and practical applications to data processing. Sensors, 24(15), Article 4806. https://doi.org/10.3390/s24154806

Zhang, R., Li, J., Liu, H., Wang, Y., & Zhang, T. (2024). Optimal gas sensor combination selection method for low-cost electronic nose. Sensors and Actuators A: Physical, 366, Article 114904.

Chen, Y., Fu, J., Weng, X., Chen, J., Hu, R., and Zhu, Y. (2024). A feature extractor for temporal data of electronic nose based on parallel long short-term memory network in flavor discrimination of Chinese vinegars. Journal of Food Engineering, 379, Article 112132. doi:10.1016/j.jfoodeng.2024.112132

Ijaz, U., Ali, M., Ahmad, I., Hamza, S. A., and Kim, H. D. (2025). A comprehensive review of electronic nose systems: Design, sensors, and future directions. Chemical Engineering Journal, 524, Article 169482. doi:10.1016/j.cej.2025.169482

Niu, G., Zhang, Y., Yu, H., Liu, Y., Li, Y., and Chen, X. (2024). Selective discrimination of VOC gases at ppb level using dynamic features extracted from temperature-pulsed MOS gas sensors. Chemosensors and Intelligent Laboratory Systems, 245, Article 105062.

Sanislav, T., Mois, G. D., Zeadally, S., Folea, S., Radoni, T. C., and Al-Suhaimi, E. A. (2025). A comprehensive review on sensor-based electronic nose for food quality and safety. Sensors, 25(14), Article 4437. doi:10.3390/s25144437

Zhai, Z., Liu, Y., Li, C., Wang, D., and Wu, H. (2024). Electronic noses: From gas-sensitive components and practical applications to data processing. Sensors, 24(15), Article 4806. doi:10.3390/s24154806

Zhang, W., Yuan, Z., Zhu, H., Zhang, S., and Meng, F. (2024). Kinetic modeling in temperature-modulated semiconductor gas sensor utilizing Eley–Rideal mechanism and its application in discriminative detection of VOCs. ACS Sensors, 9(12), 6460–6470. doi:10.1021/acssensors.4c01835

Chen, Y., Fu, J., Weng, X., Chen, J., Hu, R., & Zhu, Y. (2024). A feature extractor for temporal data of electronic nose based on parallel long short-term memory network in flavor discrimination of Chinese vinegars. Journal of Food Engineering, 379, Article 112132. https://doi.org/10.1016/j.jfoodeng.2024.112132

Sanislav, T., Mois, G. D., Zeadally, S., Folea, S., Radoni, T. C., & Al-Suhaimi, E. A. (2025). A comprehensive review on sensor-based electronic nose for food quality and safety. Sensors, 25(14), Article 4437. https://doi.org/10.3390/s25144437

Zhai, Z., Liu, Y., Li, C., Wang, D., & Wu, H. (2024). Electronic noses: From gas-sensitive components and practical applications to data processing. Sensors, 24(15), Article 4806. https://doi.org/10.3390/s24154806

Zhang, W., Yuan, Z., Zhu, H., Zhang, S., & Meng, F. (2024). Kinetic modeling in temperature-modulated semiconductor gas sensor utilizing Eley–Rideal mechanism and its application in discriminative detection of VOCs. ACS Sensors, 9(12), 6460–6470. https://doi.org/10.1021/acssensors.4c01835

Chen, Y., Fu, J., Weng, X., Chen, J., Hu, R., & Zhu, Y. (2024). A feature extractor for temporal data of electronic nose based on parallel long short-term memory network in flavor discrimination of Chinese vinegars. Journal of Food Engineering, 379, Article 112132. https://doi.org/10.1016/j.jfoodeng.2024.112132

Ijaz, U., Ali, M., Ahmad, I., Hamza, S. A., & Kim, H. D. (2025). A comprehensive review of electronic nose systems: Design, sensors, and future directions. Chemical Engineering Journal, 524, Article 169482. https://doi.org/10.1016/j.cej.2025.169482

Sanislav, T., Mois, G. D., Zeadally, S., Folea, S., Radoni, T. C., & Al-Suhaimi, E. A. (2025). A comprehensive review on sensor-based electronic nose for food quality and safety. Sensors, 25(14), Article 4437. https://doi.org/10.3390/s25144437

Zhai, Z., Liu, Y., Li, C., Wang, D., & Wu, H. (2024). Electronic noses: From gas-sensitive components and practical applications to data processing. Sensors, 24(15), Article 4806. https://doi.org/10.3390/s24154806

Chen, Y., Fu, J., Weng, X., Chen, J., Hu, R., & Zhu, Y. (2024). A feature extractor for temporal data of electronic nose based on parallel long short-term memory network in flavor discrimination of Chinese vinegars. Journal of Food Engineering, 379, 112132.

Richards, F. J. (1959). A flexible growth function for empirical use. Journal of Experimental Botany, 10(2), 290–301.

Sanislav, T., Mois, G. D., Zeadally, S., Folea, S., Radoni, T. C., & Al-Suhaimi, E. A. (2025). A comprehensive review on sensor-based electronic nose for food quality and safety. Sensors, 25(14), 4437.

Zhai, Z., Liu, Y., Li, C., Wang, D., & Wu, H. (2024). Electronic noses: From gas-sensitive components and practical applications to data processing. Sensors, 24(15), 4806.

Zhang, W., Yuan, Z., Zhu, H., Zhang, S., & Meng, F. (2024). Kinetic modeling in temperature-modulated semiconductor gas sensor utilizing Eley–Rideal mechanism and its application in discriminative detection of VOCs. ACS Sensors, 9(12), 6460–6470.

Chen, Y., Fu, J., Weng, X., Chen, J., Hu, R., and Zhu, Y. (2024). A feature extractor for temporal data of electronic nose based on parallel long short-term memory network in flavor discrimination of Chinese vinegars. Journal of Food Engineering, 379, Article 112132. https://doi.org/10.1016/j.jfoodeng.2024.112132

Sanislav, T., Mois, G. D., Zeadally, S., Folea, S., Radoni, T. C., and Al-Suhaimi, E. A. (2025). A comprehensive review on sensor-based electronic nose for food quality and safety. Sensors, 25(14), Article 4437. https://doi.org/10.3390/s25144437

Zhai, Z., Liu, Y., Li, C., Wang, D., and Wu, H. (2024). Electronic noses: From gas-sensitive components and practical applications to data processing. Sensors, 24(15), Article 4806. https://doi.org/10.3390/s24154806

Zhang, W., Yuan, Z., Zhu, H., Zhang, S., and Meng, F. (2024). Kinetic modeling in temperature-modulated semiconductor gas sensor utilizing Eley–Rideal mechanism and its application in discriminative detection of VOCs. ACS Sensors, 9(12), 6460–6470. https://doi.org/10.1021/acssensors.4c01835

Richards, F. J. (1959). A flexible growth function for empirical use. Journal of Experimental Botany, 10(2), 290–301. https://doi.org/10.1093/jxb/10.2.290

Zhai, Z., Liu, Y., Li, C., Wang, D., & Wu, H. (2024). Electronic noses: From gas-sensitive components and practical applications to data processing. Sensors, 24(15), 4806. https://doi.org/10.3390/s24154806

Zhang, W., Yuan, Z., Zhu, H., Zhang, S., & Meng, F. (2024). Kinetic modeling in temperature-modulated semiconductor gas sensor utilizing Eley–Rideal mechanism and its application in discriminative detection of VOCs. ACS Sensors, 9(12), 6460–6470. https://doi.org/10.1021/acssensors.4c01835

Chen, Y., Fu, J., Weng, X., Chen, J., Hu, R., & Zhu, Y. (2024). A feature extractor for temporal data of electronic nose based on parallel long short-term memory network in flavor discrimination of Chinese vinegars. Journal of Food Engineering, 379, Article 112132. https://doi.org/10.1016/j.jfoodeng.2024.112132

Portet, S. (2020). A primer on model selection using the Akaike information criterion. Infectious Disease Modelling, 5, 111–128. https://doi.org/10.1016/j.idm.2019.12.010