A Hybrid Electronic Nose and Computer Vision System for Non Destructive Detection of Sulfur Dioxide (SO₂) Residues in Raisins

Ghoushchian, Mohammad; Mohtasebi, Seyed Saeid; Rafiee, Shahin

doi:10.22103/bbr.2026.27286.1154

A Hybrid Electronic Nose and Computer Vision System for Non Destructive Detection of Sulfur Dioxide (SO₂) Residues in Raisins

Articles in Press

Document Type : Original Research

Authors

Mohammad Ghoushchian

Seyed Saeid Mohtasebi

Shahin Rafiee

Department of Agricultural Machinery Engineering, Faculty of Agriculture, College of Agriculture & Natural Resources, University of Tehran, Karaj, Iran

10.22103/bbr.2026.27286.1154

Abstract

Sulfur dioxide (SO₂) is widely used as a preservative in raisins, but excessive residues harm health and restrict exports. Standard iodometric titration (ISIRI No. 545) is accurate yet destructive, slow, and requires a well‑equipped laboratory. This study developed a low‑cost, portable, non‑destructive hybrid system combining an electronic nose (E‑nose) and computer vision. Three raisin treatments (sun‑dried, acid‑dipped, and sulfur‑fumigated‑then‑acid‑dipped) were prepared, each with three replicates. The E‑nose used eight MOS sensors (MQ9, MQ3, MQ5, TGS2620, MQ135, TGS822, TGS813, and MQ4). Sensor responses were recorded for 60 minutes. RAW images were captured in a dark box (2500 lux). After segmentation, 13 color components (RGB, HSV, L*a*b*, grayscale) were extracted, and six first‑order statistical features per component gave 98 features per image. Gradient Boost Regression (GBR) achieved R² = 0.9972 and RMSE = 0.0031 on test data – far better than linear regression. Sensors MQ9, MQ3, MQ5, and TGS2620 were the most accurate (R² = 0.8668–0.9458). ANOVA showed significant effects of treatment and sensor (p < 0.001). An artificial neural network (two hidden layers, 6 and 8 neurons) reached R = 0.986 and RMSE = 0.0324. Fusing olfactory and visual data using PCA and SVM improved accuracy. The hybrid system is inexpensive (< $100), portable, battery‑powered, and includes an Android app – a practical, real‑time alternative to laboratory titration.

Keywords

Electronic Nose

Gas Sensors

Computer Vision

Raisin Quality

Sulfur Dioxide

Asadi, M., Ghasemnezhad, M., Bakhshipour, A., Olfati, J.-A., & Mirjalili, M. H. (2024). Predicting the quality attributes related to geographical growing regions in red-fleshed kiwifruit by data fusion of electronic nose and computer vision systems. BMC Plant Biology, 24(1), 13. https://doi.org/10.1186/s12870-023-04661-6

Cantín, C. M., Minas, I. S., Goulas, V., Jiménez, M., Manganaris, G. A., Michailides, T. J., & Crisosto, C. H. (2012). Sulfur dioxide fumigation alone or in combination with CO2-enriched atmosphere extends the market life of highbush blueberry fruit. Postharvest Biology and Technology, 67, 84–91. https://doi.org/10.1016/j.postharvbio.2011.12.006

Chen, Z., Zhang, G., & Zhang, F. (2026). Multimodal AI for real‐time food safety and quality: from sensors to foundation models, edge deployment, and regulation. Food science & nutrition, 14(2), e71534. https://doi.org/10.1002/fsn3.71534

Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451

Gardner, J. W., & Bartlett, P. N. (1994). A brief history of electronic noses. Sensors and Actuators B: Chemical, 18(1-3), 210–211. https://doi.org/10.1016/0925-4005(94)87085-3

Girmatsion, M., Tang, X., Zhang, Q., & Li, P. (2025). Progress in machine learning-supported electronic nose and hyperspectral imaging technologies for food safety assessment: A review. Food Research International, 209, 116285. https://doi.org/10.1016/j.foodres.2025.116285

Guerrero, R. F., & Cantos-Villar, E. (2015). Demonstrating the efficiency of sulphur dioxide replacements in wine: A parameter review. Trends in Food Science & Technology, 42(1), 27–43. https://doi.org/10.1016/j.tifs.2014.11.004

Guo, J., Zhang, K., Adade, S. Y. S. S., Lin, J., Lin, H., & Chen, Q. (2025). Tea grading, blending, and matching based on computer vision and deep learning. Journal of the Science of Food and Agriculture, 105(6), 3239–3251. https://doi.org/10.1002/jsfa.14088

Institute of Standards and Industrial Research of Iran (ISIRI). (2014). Gheisi (whole dried apricot) specifications and test methods (National Standard No. 13, 4th rev.). Tehran, Iran.

Institute of Standards and Industrial Research of Iran (ISIRI). (2015). Dried apricots: Specification and test methods (National Standard No. 11, 5th rev.). Tehran, Iran.

Institute of Standards and Industrial Research of Iran (ISIRI). (2017). Dried fruits: Determination of sulfur dioxide (National Standard No. 569). Tehran, Iran.

Institute of Standards and Industrial Research of Iran (ISIRI). (2018). Specification and methods of test for fruit snack (fruit paste) (National Standard No. 3308, 2nd rev.). Tehran, Iran.

Khojastehnazhand, M., & Ramezani, H. (2020). Machine vision system for classification of bulk raisins using texture features. Journal of Food Engineering, 271, 109864. https://doi.org/10.1016/j.jfoodeng.2019.109864

Khulal, U., Zhao, J., Hu, W., & Chen, Q. (2016). Nondestructive quantifying total volatile basic nitrogen (TVB-N) content in chicken using hyperspectral imaging (HSI) technique combined with different data dimension reduction algorithms. Food chemistry, 197, 1191–1199. https://doi.org/0.1016/j.foodchem.2015.11.084

Kiani, S., Minaei, S., & Ghasemi-Varnamkhasti, M. (2017). Integration of computer vision and electronic nose as non-destructive systems for saffron adulteration detection. Computers and Electronics in Agriculture, 141, 46–53. https://doi.org/10.1016/j.compag.2017.06.018

Laganà, P., Avventuroso, E., Romano, G., Gioffré, M. E., Patanè, P., Parisi, S., Moscato, U., & Delia, S. (2017). The Codex Alimentarius and the European legislation on food additives. In Chemistry and hygiene of food additives (pp. 23–32). Springer. https://doi.org/10.1007/978-3-319-57042-6_2

Liu, Y., Wang, Q., Xu, Q., Feng, J., Yu, H., & Yin, Y. (2018). Non-destructive detection of Flos Lonicerae treated by sulfur fumigation based on hyperspectral imaging. Journal of Food Measurement and Characterization, 12(4), 2809–2818. https://doi.org/10.1007/s11694-018-9896-z

Mehraban Sangatash, M., Mahmoodi, Z., Poorazarang, H., Vosough, A. S., & Nozary Aval, Y. (2015). Determination of sulfur dioxide residue and some physicochemical properties of raisin varieties produced in Khorasan Razavi Province. Journal of Food Hygiene, 5(3), 49–58. (In Persian)

Meng, Z., Qin, G., & Zhang, B. (2005). DNA damage in mice treated with sulfur dioxide by inhalation. Environmental and molecular mutagenesis, 46(3), 150–155. https://doi.org/10.1002/em.20142

Mischek, D., & Krapfenbauer-Cermak, C. (2012). Exposure assessment of food preservatives (sulphites, benzoic and sorbic acid) in Austria. Food Additives & Contaminants: Part A, 29(3), 371–382. https://doi.org/10.1080/19440049.2011.643415

Pathmanaban, P., Gnanavel, B., & Anandan, S. S. (2019). Recent application of imaging techniques for fruit quality assessment. Trends in Food Science & Technology, 94, 32–42. https://doi.org/10.1016/j.tifs.2019.10.004

Quan, H., Sun, J., Zhou, T., Chen, T., Niu, Z., & Ma, X. (2024). Research on gas recognition based on gas sensor array and feature analysis. IEEE Sensors Journal, 24(15), 24958–24971. https://doi.org/10.1109/JSEN.2024.3409680

Soubra, L., Sarkis, D., Hilan, C., & Verger, P. (2007). Dietary exposure of children and teenagers to benzoates, sulphites, butylhydroxyanisol (BHA) and butylhydroxytoluen (BHT) in Beirut (Lebanon). Regulatory toxicology and pharmacology, 47(1), 68–77. https://doi.org/10.1016/j.yrtph.2006.07.005

Stražanac, D., Gross-Bošković, A., Hengl, B., Bašić, S., & Sokolić, D. (2019). Use of sulphur dioxide and sulphites (E 220–E 228) in canning of crab meat. Meso: prvi hrvatski časopis o mesu, 21(3.), 269–278. https://doi.org/10.31727/m.21.3.5

Türkyılmaz, M., Tağı, Ş., Dereli, U., & Özkan, M. (2013). Effects of various pressing programs and yields on the antioxidant activity, antimicrobial activity, phenolic content and colour of pomegranate juices. Food chemistry, 138(2-3), 1810–1818. https://doi.org/10.1016/j.foodchem.2012.11.100

Vally, H., Misso, N. L., & Madan, V. (2009). Clinical effects of sulphite additives. Clinical & Experimental Allergy, 39(11), 1643–1651. https://doi.org/10.1111/j.1365-2222.2009.03362.x

Wang, C. N., Li, Y. L., Gong, F. L., Zhang, Y. H., Fang, S. M., & Zhang, H. L. (2020). Advances in doped ZnO nanostructures for gas sensor. The Chemical Record, 20(12), 1553–1567. https://doi.org/10.1002/tcr.202000088

Wang, Q., & Wang, T. (2026). Machine learning-driven sensor fusion for precision agriculture: current applications and future perspectives. Sensor Review, 46(1), 1–26. https://doi.org/10.1108/SR-08-2025-0613

Yang, Y., Shahbeik, H., Shafizadeh, A., Masoudnia, N., Rafiee, S., Zhang, Y., Pan, J., Tabatabaei, M., & Aghbashlo, M. (2022). Biomass microwave pyrolysis characterization by machine learning for sustainable rural biorefineries. Renewable Energy, 201, 70–86. https://doi.org/10.1016/j.renene.2022.11.028