Hyperspectral Method Integrated with Machine Learning to Predict the Acidity and Soluble Solid Content Values of Kiwi Fruit During the Storage Period

Mansourialam, Amir; Rasekh, Mansour; Ardabili, Sina; Dadkhah, Majid; Mosavi, Amir

doi:10.2478/ata-2024-0025

Abstract

Non-destructive evaluation is advancing in examining the properties of fruits. Kiwi fruit stands out as one of the popular fruits globally. Due to the influence of various environmental factors and storage conditions, diligent checking and storage of this fruit are essential. Therefore, monitoring changes in its properties during storage in cold storage facilities is crucial. One nondestructive method utilised in recent years to investigate changes in fruit texture is the hyperspectral method. This study uses the support vector machine (SVM) method to assess hyperspectral method‘s effectiveness in examining property changes in four kiwi varieties during storage in addition to predicting the properties such as acidity and soluble solid content. The evaluation of the predictive machine learning model revealed an accuracy of 95% in predicting acidity and soluble solid content (SSC) changes in kiwi fruit during storage. Further, investigations found that the support vector machine method provided relatively lower accuracy and sensitivity in identifying product variety during storage, with an average accuracy ranging from about 91% to 94%. These findings suggest that integrating machine learning methods with outputs from techniques like hyperspectral imaging enhances the non-destructive detection capability of fruits. This integration transforms obtained results into practical outcomes, serving as an interface between software and hardware.

References

ASSAAD, M. 2020. Non-destructive, non-invasive, in-line real-time phase-based reflectance for quality monitoring of fruit. In International Journal on Smart Sensing and Intelligent Systems, vol. 13, no. 1, pp. 1–10. DOI: https://doi.org/10.21307/ijssis-2020-009
Search in Google Scholar Back to article
BENELLI, A. – CEVOLI, C. – FABBRI, A. – RAGNI, L. 2022. Ripeness evaluation of kiwifruit by hyperspectral imaging. In Biosystems Engineering, vol. 223, part B, pp. 42–52. DOI: https://doi.org/10.1016/j.biosystemseng.2021.08.009
Search in Google Scholar Back to article
CHEŁPIŃSKI, P. – OCHMIAN, I. – FORCZMAŃSKI, P. 2019. Sweet cherry skin colour measurement as an non-destructive indicator of fruit maturity. In Acta Universitatis Cibiniensis. Series E: Food Technology, vol. 23, no. 2, pp. 157–166. DOI: https://doi.org/10.2478/aucft-2019-0019
Search in Google Scholar Back to article
EBRAHIMI, S. – POURDARBANI, R. – SABZI, S. – ROHBAN, M. H. – ARRIBAS, J. I. 2023. From harvest to market: Non-destructive bruise detection in kiwifruit using convolutional neural networks and hyperspectral imaging. In Horticulturae, vol. 9, no. 8, article no. 936. DOI: https://doi.org/10.3390/horticulturae9080936
Search in Google Scholar Back to article
GEYER, M. – HEROLD, B. – ZUDE, M. – TRUPPEL, I. 2007. Nondestructive evaluation of apple fruit maturity on the tree. In Journal of Fruit and Ornamental Plant Research, vol. 66, no. 1, pp. 161–169. DOI: https://doi.org/10.2478/v10032-007-0018-4
Search in Google Scholar Back to article
KE, J. – ZHIQIANG, G. – YUNLIU, Z. – GANG, D. 2023. Hyperspectral imaging-based quality classification for kiwifruit by incorporating three-dimensional convolution neural network and haar wavelet filter. In Laser and Optoelectronics Progress, vol. 60, no. 20, pp. 41–50. DOI: https://doi.org/10.3788/LOP223142
Search in Google Scholar Back to article
LAZIM, S. S. R. M. – NAWI, M. N. – BEJO, S. K. – SHARIFF, A. R. M. – ABDULLAH, N. 2022. Prediction and classification of soluble solid contents to determine the maturity level of watermelon using visible and shortwave near infrared spectroscopy. In International Food Research Journal, vol. 29, no. 6, pp. 1372–1379. DOI: https://doi.org/10.47836/ifrj.29.6.13
Search in Google Scholar Back to article
LI, M. – PULLANAGARI, R. – YULE, I. – EAST, A. 2022. Segregation of ‘Hayward’ kiwifruit for storage potential using Vis-NIR spectroscopy. In Postharvest Biology and Technology, vol. 189, article no. 111893. DOI: https://doi.org/10.1016/j.postharvbio.2022.111893
Search in Google Scholar Back to article
LI, X. – WEI, Y. – XU, J. – FENG, X. – WU, F. – ZHOU, R. – JIN, J. – XU, K. – YU, X. – HE, Y. 2018. SSC and pH for sweet assessment and maturity classification of harvested cherry fruit based on NIR hyperspectral imaging technology. In Postharvest Biology and Technology, vol. 143, pp. 112–118. DOI: https://doi.org/10.1016/j.postharvbio.2018.05.003
Search in Google Scholar Back to article
LUE, Q. – TANG, M. – CAI, J.-R. – LU, H. – CHAITEP, S. 2010. Selection of efficient wavelengths in NIR spectrum for determination of dry matter in kiwi fruit. In Maejo International Journal of Science and Technology, vol. 4, no. 1, pp. 113–124.
Search in Google Scholar Back to article
NIU, C. – GUO, H. – WEI, J. – SAJID, M. – YUAN, Y. – YUE, T. 2018. Fourier transform near-infrared spectroscopy and chemometrics to predict Zygosacchromyces rouxii in apple and kiwi fruit juices. In Journal of Food Protection, vol. 81, no. 8, pp. 1379–1385. DOI: https://doi.org/10.4315/0362-028X.JFP-17-512
Search in Google Scholar Back to article
ONUR, T. Ö. 2022. Improved image denoising using wavelet edge detection based on Otsu’s thresholding. In Acta Polytechnica Hungarica, vol. 19, no. 2, pp. 79-92. DOI: https://doi.org/10.12700/APH.19.2.2022.2.5
Search in Google Scholar Back to article
REIS-PEREIRA, M. – TOSIN, R. – MARTINS, R. – NEVES DOS SANTOS, F. – TAVARES, F. – CUNHA, M. 2022. Kiwi plant canker diagnosis using hyperspectral signal processing and machine learning: detecting symptoms caused by Pseudomonas syringae pv. actinidiae. In Plants, 11, no. 16, article no. 2154. DOI: https://doi.org/10.3390/plants11162154
Search in Google Scholar Back to article
ROSARIO, S. F. – THANGADURAI, K. 2015. RELIEF: feature selection approach. In International Journal of Innovative Research and Development, vol. 4, no. 11, pp. 218–224.
Search in Google Scholar Back to article
SARKAR, S. – BASAK, J. K. – MOON, B. E. – KIM, H. T. 2020. A comparative study of PLSR and SVM-R with various preprocessing techniques for the quantitative determination of soluble solids content of hardy kiwi fruit by a portable Vis/NIR spectrometer. In Foods, vol. 9, no. 8, article no. 1078. DOI: https://doi.org/10.3390/foods9081078
Search in Google Scholar Back to article
SATPAL, D. – KAUR, J. – BHADARIYA, V. – SHARMA, K. 2021. Actinidia deliciosa (kiwi fruit): A comprehensive review on the nutritional composition, health benefits, traditional utilization, and commercialization. In Journal of Food Processing and Preservation, vol. 45. DOI: https://doi.org/10.1111/jfpp.15588
Search in Google Scholar Back to article
SUTHAHARAN, S. 2016. Support vector machine. In Machine Learning Models and Algorithms for Big Data Classification. Thinking with Examples for Effective Learning. New York : Springer, pp. 207–235. eISBN 978-1-4899-7641-3. DOI: https://doi.org/10.1007/978-1-4899-7641-3_9
Search in Google Scholar Back to article
TAGHINEZHAD, E. – RASOOLI SHARABIANI, V. – SHAHIRI, M. – MOINFAR, A. – SZUMNY, A. 2023. Predicting quality properties of pears during storage using hyper spectral imaging system. In Agriculture, vol. 13, no. 10, article no. 1913. DOI: https://doi.org/10.3390/agriculture13101913
Search in Google Scholar Back to article
URBANOWICZ, R. J. – MEEKER, M. – LA CAVA, W. – OLSON, R. S. – MOORE, J. H. 2018. Relief-based feature selection: Introduction and review. In Journal of Biomedical Informatics, vol. 85, pp. 189–203. DOI: https://doi.org/10.1016/j.jbi.2018.07.014
Search in Google Scholar Back to article
WANG, H. – PENG, J. – XIE, C. – BAO, Y. – HE, Y. 2015. Fruit quality evaluation using spectroscopy technology: A review. In Sensors, vol. 15, no. 5, pp. 11889–11927. DOI: https://doi.org/10.3390/s150511889
Search in Google Scholar Back to article

Hyperspectral Method Integrated with Machine Learning to Predict the Acidity and Soluble Solid Content Values of Kiwi Fruit During the Storage Period

Abstract

Paradigm

My account