Optimizing gas sensor array to classify three edible ripening stages of date fruit using machine learning and feature selection (case study: cv. Shahani.)
Abstract
Aim of study: This study aimed to analyze aroma changes in date fruits (Phoenix dactylifera L.) across three ripening stages (Khalal, Rutab, and Tamr) using an e-nose as a non-destructive monitoring method for fruit quality management. The study also evaluated feature selection methods to optimize the sensor array for a repeatable model based on external data.
Area of study: This study was carried out at a date palm garden cultivated by cv. Shahani in Jahrom, west-south of Iran.
Material and methods: An e-nose profiled the aroma of date fruits from a date palm garden across three ripening stages over two years. Classification models, developed using one year’s data as internal data, were externally validated using data from the other year as external data. Feature selection optimized the sensor array, improving the prediction accuracy on the external dataset. Main results: The classification models had similar test accuracy, but their predictive performance varied on external data. Using F-test and principal component analysis (PCA) for feature selection to optimize the sensor array, with support vector machine (SVM) as the classification algorithm, resulted in a highly repeatable model. This study suggests that e-noses are a promising tool for monitoring aroma changes during date fruit ripening in artificial ripening or storage processes.
Research highlights: Aroma profiles from edible ripening stages in data fruits were classified with high accuracy using e-nose; Feature selection methods can affect linear discriminant analysis (LDA) and SVM algorithms differently on external data; In SVM, some feature selection methods decreased prediction accuracy on external data compared to using the full sensor array; PCA effectively determined the optimal number of features for optimizing the sensor array.
Downloads
References
Al-Kaabi HJ, 2020. Effect of modified atmosphere packaging on quality of barhi dates at Khalal stage. International Journal of Food Studies, 9. https://doi.org/10.7455/ijfs/9.SI.2020.a10
Alam MZ, Al-Hamimi S, Ayyash M, Rosa CT, Yahia EM, Haris S, Al-Marzouqi AH, Kamal-Eldin A, 2023. Contributing factors to quality of date (Phoenix dactylifera L.) fruit. Scientia Horticulturae 321. https://doi.org/10.1016/j.scienta.2023.112256
Ali H, Al-Khalifa AR, Farouk A, Shaheen M, 2018. Effect of maturation stages on flavor profile and antioxidant activity of date palm fruits (Phoenix dactylifera) grown in Saudi Arabia. International Journal of Pharmacology 14(3). https://doi.org/10.3923/ijp.2018.407.414
Amira EA, Flamini G, Behija SE, Manel I, Nesrine Z, Ali F, Mohamed H, Noureddine HA, Lotfi A, 2011. Chemical and aroma volatile compositions of date palm (Phoenix dactylifera L.) fruits at three maturation stages. Food Chemistry 127(4). https://doi.org/10.1016/j.foodchem.2011.02.051
Aouadi B, Zaukuu JLZ, Vitális F, Bodor Z, Fehér O, Gillay Z, Bazar G, Kovacs Z, 2020. Historical evolution and food control achievements of near infrared spectroscopy, electronic nose, and electronic tongue—critical overview. Sensors 20(19). https://doi.org/10.3390/s20195479
Banon C, Triawan DA, Adfa M, Sihite MSA, Nurwidiyani R, Rahmi W, 2024. Classification of Makasar Fruit Extract (Brucea javanica L. Merr.) Based on The Level of Ripeness Using a Combination of FTIR and UV-Vis Spectroscopy with Chemometrics. Jurnal Kimia Sains Dan Aplikasi 26(12). https://doi.org/10.14710/jksa.26.12.483-488
Beghi R, Buratti S, Giovenzana V, Benedetti S, Guidetti R, 2017. Electronic nose and visible-near infrared spectroscopy in fruit and vegetable monitoring. Reviews in Analytical Chemistry 36(4). https://doi.org/10.1515/revac-2016-0016
Bhalaji N, Sundhara Kumar KB, Selvaraj C, 2018. Empirical study of feature selection methods over classification algorithms. International Journal of Intelligent Systems Technologies and Applications 17(1–2). https://doi.org/10.1504/IJISTA.2018.091590
Cıbuk M, Budak U, Guo Y, Cevdet Ince M, Sengur A, 2019. Efficient deep features selections and classification for flower species recognition. Measurement 137. https://doi.org/10.1016/j.measurement.2019.01.041
Dhanya R, Paul IR, Sindhu Akula S, Sivakumar M, Nair JJ, 2019. A comparative study for breast cancer prediction using machine learning and feature selection. International Conference on Intelligent Computing and Control Systems (ICCS 2019). https://doi.org/10.1109/ICCS45141.2019.9065563
Du D, Wang J, Wang B, Zhu L, Hong X, 2019. Ripeness prediction of postharvest Kiwifruit using a MOS E-nose combined with chemometrics. Sensors 19(2). https://doi.org/10.3390/s19020419
Echegaray N, Gullón B, Pateiro M, Amarowicz R, Misihairabgwi JM, Lorenzo JM, 2021. Date Fruit and Its By-products as Promising Source of Bioactive Components: A Review. Food Reviews International. https://doi.org/10.1080/87559129.2021.1934003
Gao X, Zhang T, 2018. An overview: Facet-dependent metal oxide semiconductor gas sensors. Sensors and Actuators B: Chemical 277. https://doi.org/10.1016/j.snb.2018.08.129
Haque MM, Rahman A, Hagare D, Chowdhury RK, 2018. A comparative assessment of variable selection methods in urban water demand forecasting. Water 10(4). https://doi.org/10.3390/w10040419
Huang W, Xia J, Wang Y, Jin X, Zhu HL, Zhang X, 2024. Flexible multimode sensors based on hierarchical microstructures enable non-destructive grading of fruits in cold chain logistics. Materials Today Sustainability 25. https://doi.org/10.1016/j.mtsust.2024.100691
Jolliffe IT, 2002. Principal Component Analysis. Springer-Verlag. https://doi.org/10.1007/b98835
Jolliffe IT, Cadima J, 2016. Principal component analysis: A review and recent developments. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 374(2065), p. 20150202. https://doi.org/10.1098/rsta.2015.0202
Jović A, Brkić K, Bogunović N, 2015. A review of feature selection methods with applications. 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO 2015). https://doi.org/10.1109/MIPRO.2015.7160458
Karakaya D, Ulucan O, Turkan M, 2020. Electronic Nose and Its Applications: A Survey. International Journal of Automation and Computing. https://doi.org/10.1007/s11633-019-1212-9
Kim C, Kim SJ, Lee Y, Nguyen TM, Lee JM, Moon JS, Han DW, Oh JW, 2022. A phage- and colorimetric sensor-based artificial nose model for banana ripening analysis. Sensors and Actuators B: Chemical 362. https://doi.org/10.1016/j.snb.2022.131763
Mohammed M, Sallam A, Alqahtani N, Munir M, 2021. The combined effects of precision-controlled temperature and relative humidity on artificial ripening and quality of date fruit. Foods 10(11). https://doi.org/10.3390/foods10112636
Mohtasebi SS, Keramat-Jahromi M, Savand-Roumi E, 2019. Laboratory Olfactory Machine, Iranian Research Organization for Science and Technology (IROST), No. 1397236. DOI: 10.22104/IROST.1397.236
Moon P, Fu Y, Bai J, Plotto A, Crane J, Chambers A, 2018. Assessment of fruit aroma for twenty-seven guava (Psidium guajava) accessions through three fruit developmental stages. Scientia Horticulturae 238. https://doi.org/10.1016/j.scienta.2018.04.067
Naik MK, Wunnava A, 2020. Classical 2D face recognition: a survey on methods, face databases, and performance evaluation. Lecture Notes in Networks and Systems 109: 375–383. https://doi.org/10.1007/978-981-15-2774-6_45
Pan L, Li H, Hu Z, Zhang M, Zhao J, 2024. Standard-free sample model transfer of visible/near-infrared spectral model of apple ripeness under seasonal variation. Journal of Food Composition and Analysis 128. https://doi.org/10.1016/j.jfca.2024.106028
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay É, 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 12: 2825–2830. http://scikit-learn.sourceforge.net
Pineau J, Vincent-Lamarre P, Sinha K, Lariviére V, Beygelzimer A, d’Alché-Buc F, Fox E, Larochelle H, 2021. Improving reproducibility in machine learning research (a report from the NeurIPS 2019 reproducibility program). Journal of Machine Learning Research 22.
Rahman MS, Al-Farsi K, Al-Maskari SS, Al-Habsi NA, 2018. Stability of electronic nose (e-nose) as determined by considering date pits heated at different temperatures. International Journal of Food Properties. https://doi.org/10.1080/10942912.2018.1463540
Rahmani K, Thapa R, Tsou P, Casie Chetty S, Barnes G, Lam C, Foon Tso C, 2023. Assessing the effects of data drift on the performance of machine learning models used in clinical sepsis prediction. International Journal of Medical Informatics 173. https://doi.org/10.1016/j.ijmedinf.2022.104930
Rizzo M, Marcuzzo M, Zangari A, Gasparetto A, Albarelli A, 2023. Fruit ripeness classification: A survey. Artificial Intelligence in Agriculture 7. https://doi.org/10.1016/j.aiia.2023.02.004
Savand-Roumi E, Salehiyoun AR, Mohtasebi SS, 2024. Use of a biogas-specific e-nose with machine learning to identify biogas pattern changes linked to hydraulic retention times in an anaerobic digester: A case study. Fuel 357: 130013. https://doi.org/10.1016/j.fuel.2023.130013
Se H, Song K, Sun C, Jiang J, Liu H, Wang B, Wang X, Zhang W, Liu J, 2024. Online drift compensation framework based on active learning for gas classification and concentration prediction. Sensors and Actuators B: Chemical 398: 134716. https://doi.org/10.1016/j.snb.2023.134716
Sudha C, Mohan KJ, 2023. E-Nose for Cashew Apple Ripeness Detection for Autonomous Fruit Plucking. SSRG International Journal of Electronics and Communication Engineering 10(10). https://doi.org/10.14445/23488549/IJECE-V10I10P105
Tong J, Song C, Tong T, Zong X, Liu Z, Wang S, Tan L, Li Y, Chang Z, 2022. Design and Optimization of Electronic Nose Sensor Array for Real-Time and Rapid Detection of Vehicle Exhaust Pollutants. Chemosensors 10(12). https://doi.org/10.3390/chemosensors10120496
Ulivieri N, Distante C, Luca T, Rocchi S, Siciliano P, 2006. IEEE1451.4: A way to standardize gas sensor. Sensors and Actuators B: Chemical 114(1). https://doi.org/10.1016/j.snb.2005.04.044
Voss HGJ, Ayub RA, Stevan SL, 2020. E-nose Prototype to Monitoring the Growth and Maturation of Peaches in the Orchard. IEEE Sensors Journal 20(20): 11741–11750.
Wang X, Zhao W, Ma R, Zhuo J, Zeng Y, Wu P, Chu J, 2024. A novel high accuracy fast gas detection algorithm based on multitask learning. Measurement 228: 114383. https://doi.org/10.1016/J.MEASUREMENT.2024.114383
Wang Y, Ma X, Qian P, 2018. Wind Turbine Fault Detection and Identification Through PCA-Based Optimal Variable Selection. IEEE Transactions on Sustainable Energy 9(4). https://doi.org/10.1109/TSTE.2018.2801625
Watson NE, Parsons BA, Synovec RE, 2016. Performance evaluation of tile-based Fisher Ratio analysis using a benchmark yeast metabolome dataset. Journal of Chromatography A 1459: 101–111. https://doi.org/10.1016/j.chroma.2016.06.067
Xiao B, Nguyen M, Yan WQ, 2024. Fruit ripeness identification using YOLOv8 model. Multimedia Tools and Applications 83(9). https://doi.org/10.1007/s11042-023-16570-9
Yan J, Guo X, Duan S, Jia P, Wang L, Peng C, Zhang S, 2015. Electronic Nose Feature Extraction Methods: A Review. Sensors 15: 27804–27831. https://doi.org/10.3390/s151127804
Yan K, Zhang D, 2016. Calibration transfer and drift compensation of e-noses via coupled task learning. Sensors and Actuators B: Chemical 225. https://doi.org/10.1016/j.snb.2015.11.058
Zhang X, Li Y, Hong T, Tegeltija S, Babić M, Wang X, Ostojić G, Marinković D, 2023. Response Characteristics Study of Ethylene Sensor for Fruit Ripening under Temperature Control. Sensors 23(11). https://doi.org/10.3390/s23115203
Copyright (c) 2025 Consejo Superior de Investigaciones Científicas (CSIC)
This work is licensed under a Creative Commons Attribution 4.0 International License.
© CSIC. Manuscripts published in both the print and online versions of this journal are the property of the Consejo Superior de Investigaciones Científicas, and quoting this source is a requirement for any partial or full reproduction.
All contents of this electronic edition, except where otherwise noted, are distributed under a Creative Commons Attribution 4.0 International (CC BY 4.0) licence. You may read the basic information and the legal text of the licence. The indication of the CC BY 4.0 licence must be expressly stated in this way when necessary.
Self-archiving in repositories, personal webpages or similar, of any version other than the final version of the work produced by the publisher, is not allowed.
