Remaining shelf-life prediction of squid using handheld Vis/NIR spectroscopy and ensemble learning
Keywords:
squid freshness, handheld spectrometer, spatial heterogeneity, stacked ensemble learning, kinetic modeling, remaining shelf life (RSL)Abstract
To address the limitations of traditional squid freshness assessment, which relies on destructive physicochemical indicators and neglects anatomical spatial heterogeneity—thereby compromising on-site accuracy—this study developed an integrated handheld visible and near-infrared (Vis-NIR) spectroscopy system combined with intelligent algorithms. A multi-scale decomposition of spectral signals (450-950 nm) was innovatively performed using Discrete Wavelet Transform (DWT) to extract energy spectrum features. By integrating Isolation Forest for outlier rejection and a Stacked Ensemble Learning framework (Stacking: base=Ridge/RF/HGBR, meta=GBR), a robust prediction model for storage time was constructed. The experimental results demonstrated that the proposed model achieved an excellent coefficient of determination (R2=0.9528), a Root Mean Square Error (RMSE=0.6566 d), and a Residual Prediction Deviation (RPD=4.60) on the validation set, with uniformly distributed residuals cross-verified by the Breusch–Pagan test (p=0.6944). Weibull kinetic modeling revealed distinct degradation patterns across anatomical sites; specifically, the abdominal region exhibited a maximum shape parameter (=1.787) and a massive Akaike Information Criterion advantage (AIC=490.6) over the first-order kinetic paradigm, indicating an accelerating, self-catalytic quality degradation profile driven by endogenous visceral enzymes. Finally, the real-time predicted storage time was successfully coupled with local Weibull parameters to output probabilistic Remaining Shelf Life (RSL) profiles via Kernel Density Estimation (KDE), which establishes a proactive digital traceability pipeline for precision grading and dynamic inventory management of high-value marine aquatic products.
Key words: squid freshness; handheld spectrometer; spatial heterogeneity; stacked ensemble learning; kinetic modeling; remaining shelf life (RSL)
DOI: 10.25165/j.ijabe.20261904.10501
Citation: Miao X, Sun Y J, Tong A Y, Bao W S, Liu C C, Cao S Q, et al. Remaining shelf-life prediction of squid using
handheld Vis/NIR spectroscopy and ensemble learning. Int J Agric & Biol Eng, 2026; 19(4): 338–346.
References
[1] FAO. The state of world fisheries and aquaculture 2024. Rome: Food and Agriculture Organization of the United Nations, 2024.
[2] Tidwell J H, Allan G L. Fish as food: Aquaculture’s contribution. EMBO Reports, 2001; 2: 958–963.
[3] China Distant-water Fisheries Association. 2024 development report of China’s distant-water squid jigging industry. Beijing: China Distant-water Fisheries Association. 2024. （in Chinese）
[4] Goulas A E, Kontominas M G. Combined effect of light salting, modified atmosphere packaging and oregano essential oil on the shelf-life of sea bream （Sparus aurata）: Biochemical and sensory attributes. Food Chemistry, 2007; 100（1）: 287–296.
[5] Gram L, Dalgaard P. Fish spoilage bacteria–problems and solutions. Current Opinion in Biotechnology, 2002; 13（3）: 262–266.
[6] Bekhit A E D A, Holman B W B, Giteru S G, Hopkins D L. Total volatile basic nitrogen （TVB-N） and its role in meat spoilage: A review. Trends in Food Science & Technology, 2021; 109: 280–302.
[7] Wang H, He H J, Liu L, Ma H J, Liu X, Mo H Z, et al. Recent progress in hyperspectral imaging for nondestructive evaluation of fish quality. Food Science, 2019; 40（5）: 329–338. （in Chinese）
[8] Ocaño-Higuera V M, Maeda-Martínez A N, Marquez-Ríos E, Canizales-Rodríguez D F, Castillo-Yáñez F J, Ruíz-Bustos E, et al. Freshness assessment of ray fish stored in ice by biochemical, chemical and physical methods. Food Chemistry, 2011; 125（1）: 49–54.
[9] Ruiz-Capillas C, Moral A. Correlation between biochemical and sensory quality indices in hake stored in ice. Food Research International, 2001; 34（5）: 441–447.
[10] Özogul F, Polat A, Özogul Y. The effects of modified atmosphere packaging and vacuum packaging on chemical, sensory and microbiological changes of sardines （Sardina pilchardus）. Food Chemistry, 2004; 85（1）: 49–57.
[11] Mawrides E K, Mishra A, Jæger B. Blockchain technology for sustainable supply chains in the fishing industry: A systematic review. Cleaner Logistics and Supply Chain, 2025; 17: 100277.
[12] Lougovois V P, Kyranas E R, Kyrana V R. Comparison of selected methods of assessing freshness quality and remaining storage life of iced Gilthead sea bream （Sparus aurata）. Food Research International, 2003; 36（5）: 551–560.
[13] Howgate P. A review of the kinetics of degradation of inosine monophosphate in some species of fish during chilled storage. International Journal of Food Science and Technology, 2006; 41（4）: 341–353.
[14] Yu Q, Zhang M, Mujumdar A S, Huang M. Real-time spoilage monitoring of aquatic products using advanced sensors and novel equipment. Journal of Food Measurement and Characterization, 2026; 20（9）: 3829–3850.
[15] GB 5009.228-2016. National food safety standard - Determination of volatile basic nitrogen in foods. Beijing: National Health and Family Planning Commission of the PRC, 2016. （in Chinese）
[16] Tsoukalas D, Lerfall J, Jakobsen A N. Insights into the quality changes of edible sea urchin （Echinus esculentus） gonads during ice storage. LWT, 2024; 203: 116345.
[17] Wu D, Sun D W. Advanced applications of hyperspectral imaging technology for food quality and safety analysis and assessment: A review — Part I: Fundamentals. Innovative Food Science & Emerging Technologies, 2013; 19: 1–14.
[18] Kashani Zadeh H, Hardy M, Sueker M, Li Y C, Tzouchas A, MacKinnon N, et al. Rapid assessment of fish freshness for multiple supply-chain nodes using multi-mode spectroscopy and fusion-based artificial intelligence. Sensors, 2023; 23（11）: 5149.
[19] El Masry G, Wang N, El Sayed A, Ngadi M. Hyperspectral imaging for nondestructive determination of some quality attributes for strawberry. Journal of Food Engineering, 2007; 81（1）: 98–107.
[20] Hardy M, Moser B, Haughey S A, Elliott C T. Does the fish rot from the head? Hyperspectral imaging and machine learning for the evaluation of fish freshness. Chemometrics and Intelligent Laboratory Systems, 2024; 245（80）: 105059.
[21] Zhang Q Y, Hu Z G, Xu Z J, Zhang P L, Jiang Y J, Fu D D, et al. Quantitative determination of TVB-N content for different types of refrigerated grass carp fillets using near-infrared spectroscopy combined with machine learning. Journal of Food Composition and Analysis, 2024; 126: 105871.
[22] Zhang Y J, Wang M P, Yang G H, Li J, Zhu G F, Shi J F, et al. Optical simulation model of the diffuse reflectance near-infrared spectroscopy for predicting fresh maize quality. Int J Agric & Biol Eng, 2025; 18（6）: 250–259.
[23] Cozzolino D. Near infrared spectroscopy and food authenticity. In: Espiñeira M, Santaclara F J （Eds.）. Advances in Food Traceability Techniques and Technologies. Cambridge: Woodhead Publishing, 2016; pp.119–136.
[24] Wu X D, Wang Z M, Wang Z Q, Zhang Q, Zhang Q X, Yan H B, et al. Prediction method of large yellow croaker （Larimichthys crocea） freshness based on improved residual neural network. Journal of Food Measurement and Characterization, 2024; 18（4）: 2995–3007.
[25] Wu S, Huang L F, Huang R S. Review of advances in hyper-spectral imaging-based non-destructive testing methods in food application. Journal of Food Composition and Analysis, 2026; 150: 108860.
[26] Xu Z, Zhu S C, Wang W J, Liu S L, Zhou X X, Dai W L, et al. Rapid and non-destructive freshness evaluation of squid by FTIR coupled with chemometric techniques. Journal of the Science of Food and Agriculture, 2021; 102: 3000–3009.
[27] Ahmed Z, Donkor O, Street W A, Vasiljevic T. Calpains- and cathepsins-induced myofibrillar changes in post-mortem fish: Impact on structural softening and release of bioactive peptides. Trends in Food Science & Technology, 2015; 45（1）: 130–146.
[28] Yu H D, Zuo S M, Xia G H, Liu X, Yun Y H, Zhang C. Rapid and nondestructive freshness determination of tilapia fillets by a portable near-infrared spectrometer combined with chemometrics methods. Food Analytical Methods, 2020; 13（10）: 1918–1928.
[29] Mallat S. A wavelet tour of signal processing: The sparse way. 3rd ed., Academic Press, 2009. doi: 10.1016/B978-0-12-374370-1.X0001-8
[30] Peleg M, Normand M D, Corradini M G. The Arrhenius equation revisited. Critical Reviews in Food Science and Nutrition, 2012; 52（9）: 830–851.
[31] Xu G, Dong L Q, Kong L Q, Zhao Y J, Liu M, Hui M, et al. Parameters inversion algorithm of biological tissues based on a neural network model. Acta Optica Sinica, 2021; 41（11）: 1117001. （in Chinese） doi: 10.3788/aos202141.1117001
[32] Chong W, Lyu W H, Zhang J, Liang J, Yang X T, Liu S, et al. Calibration system of sunshine duration recorder based on bi-xenon lamp source integrating sphere. Acta Optica Sinica, 2022; 42（1）: 0112004. （in Chinese）
[33] Gao Y W, Geng J F, Rao X Q. Non-invasive bruise detection in postharvest fruits and vegetables: A review. Food Science, 2017; 38（15）: 277–287. （in Chinese）
[34] Zhang Y L, Yang G H, Wang M P, Han Z Y, Zhu G F, Shi J F, et al. Factors affecting the non-destructive detection of water contents in fresh corn cobs by near-infrared spectroscopy. Transactions of the CSAE, 2024; 40（15）: 262–270. （in Chinese）
[35] Lanke N P, Chandak M B. Recent trends in deep learning and hyperspectral imaging for fruit quality analysis: An overview. Journal of Optics, 2025; 54: 1–15.
[36] Bashkatov A N, Genina E A, Tuchin V V. Optical properties of skin, subcutaneous, and muscle tissues: A review. Journal of Innovative Optical Health Sciences, 2011; 4（1）: 9–38.
[37] Beć K B, Grabska J, Huck C W. Chapter Six - Handheld NIR spectroscopy for real-time on-site food quality and safety monitoring. Advances in Food and Nutrition Research, 2025; 115: 293–389.
[38] Iqbal M, Yousaf J, Khan A, Muhammad T. IoT-enabled food freshness detection using multi-sensor data fusion and mobile sensing interface. ICCK Transactions on Sensing, Communication, and Control, 2025; 2（2）: 122–131.
[39] Aguilera-Barraza F A, Quevedo-León R A, López-Álvarez P X. Kinetics of protein and textural changes in Atlantic salmon under frozen storage. Food Chemistry, 2015; 182: 120–127.
[40] Chen Q, Li J L, Yang H, Qian J P. A dynamic shelf-life prediction method considering actual uncertainty: Application to fresh fruits in long-term cold storage. Journal of Food Engineering, 2023; 349: 111471.
[41] Kundu M, Vashisth A, Krishnan P. Instrumental detection of fish freshness in research and food industry: A review. Journal of Food Science and Technology, 2025; 63: 22–50.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Agricultural and Biological Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
IJABE is an international peer reviewed, open access journal, adopting Creative Commons Copyright Notices as follows.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
