Sürdürülebilir Kalkınma Amaçları

• 2
• 1

Yazarlar

• Akpolat, Hacer(2)
• Abca, Tuğba Elbir(1)
• Akpolat, Mehmet Z.(1)
• Akpolat, Mehmet Zahid(1)
• Barineau, Mark(1)
• Baştürk, Fatma Nur(1)
• Chen, Yu-Ju(1)
• Ecem Bayram, Nesrin(1)
• Francis, David M.(1)
• Fuente-Ballesteros, Adrián(1)
• Gerçek, Yusuf Can(1)
• Gıdık, Betül(1)
• Jackson, Keith A.(1)
• Kutlu, Naciye(1)
• Rodriguez-Saona, Luis E.(1)
• Yurtvermez, Bayram(1)

• MakaleYalnız künye2026Scopus SJRQ2/r/bayburt/11378
  Leakage-safe benchmarking of conventional chemometric and deep learning models for food NIR spectroscopy regression

  Akpolat, Hacer; Akpolat, Mehmet Zahid

  Near-infrared (NIR) spectroscopy is widely used in food systems for rapid, non-destructive estimation of compositional and quality attributes. Although machine-learning and deep-learning models are increasingly reported for spectral regression, practical model selection is often hindered by heterogeneous validation setups and the risk of information leakage during preprocessing and tuning. In this study, we provide a leakage-safe benchmark across nine food-related regression tasks spanning different sample sizes and spectral dimensionalities. Conventional chemometric and regression baselines (partial least squares regression, ridge regression, and support vector regression) are compared with lightweight deep-learning baselines (a shallow artificial neural network and a one-dimensional convolutional neural network) under a unified leakage-safe evaluation framework combining nested cross-validation with acomplementary fixed held-out test-set assessment, fold-wise preprocessing, and repeated training for stochastic models. Performance is summarized primarily using prediction error (RMSE in nested cross-validation and RMSEP on the held-out test set), while the coefficient of determination is retained as a secondary descriptive measure, complemented by cross-validation and fixed held-out-test learning-curve analyses together with model-complexity analysis. Across both validation analyses, ridge regression achieved the largest number of numerical task-level wins, while partial least squares regression and support vector regression remained competitive across multiple tasks. Paired randomization tests following van der Voet further showed that some small numerical differences between models were not statistically distinguishable. Artificial neural network and one-dimensional convolutional neural network baselines did not provide a reliable generalization advantage and showed greater variability in some data-limited settings. From a food-measurement perspective, these findings indicate that well-validated conventional models remain a strong default for routine NIR calibration workflows and non-destructive quality assessment. Deep learning appears most justified when calibration settings provide larger datasets, stronger experimental control, or spectroscopy-specific inductive bias that can translate added model complexity into practical measurement gains. Overall, this study serves as a controlled benchmark and reference for model selection under realistic food-spectroscopy data regimes.

  • 
  AtıfOpenAlex1

  İncele
• MakaleAçık Erişim2026Scopus SJRQ1/r/bayburt/11303
  Ultrasonic-Assisted Deep Eutectic Solvent Extraction of Polyphenols From Tea Parts: A Green Assessment

  Gerçek, Yusuf Can; Baştürk, Fatma Nur; Gıdık, Betül; Abca, Tuğba Elbir; Yurtvermez, Bayram; Fuente-Ballesteros, Adrián; Kutlu, Naciye; Ecem Bayram, Nesrin

  Deep eutectic solvents (DESs) have emerged as green alternatives to conventional solvents for extracting bioactive compounds from plants. This study evaluated nine choline chloride–based DESs for recovering antioxidant polyphenols from four parts of the tea plant (Camellia sinensis): seed, bud, leaf, and flower. Total phenolic content, antioxidant activity, and individual polyphenolic profiles were determined, and the greenness of the sample preparation was assessed using AGREEprep. The highest total phenolic content (53.28 mg GAE/g) and antioxidant activity (141.17 mg TE/g) were obtained from leaves using ChCl:formic acid, outperforming ethanol and methanol. Leaves also exhibited the highest total quantified polyphenolic content (up to 95,813 mg/kg DW, corresponding to the sum of the quantified polyphenols), with epicatechin gallate and gallocatechin + epigallocatechin being the major contributors. Flowers and buds showed notable polyphenolic diversity, while seeds contained the lowest levels. Statistical analysis confirmed clear clustering patterns according to plant part and solvent type. AGREEprep evaluation yielded scores up to 0.54, highlighting the environmental benefits of DES-based extraction. We demonstrated that tea leaves were the richest source of bioactive polyphenols, and selected DESs, particularly formic acid–based and ethylene glycol–based, exhibited superior efficiency and sustainability compared to conventional solvents. These findings support the wider adoption of DESs for green, high-yield extraction of pharmacologically important compounds from tea and other medicinal plants.

  • 
  İncele
• MakaleAçık Erişim2020Scopus SJRQ2/r/bayburt/12033
  High-throughput phenotyping approach for screening major carotenoids of tomato by handheld raman spectroscopy using chemometric methods

  Akpolat, Hacer; Barineau, Mark; Jackson, Keith A.; Akpolat, Mehmet Z.; Francis, David M.; Chen, Yu-Ju; Rodriguez-Saona, Luis E.

  Our objective was to develop a rapid technique for the non-invasive profiling and quantification of major tomato carotenoids using handheld Raman spectroscopy combined with pattern recognition techniques. A total of 106 samples with varying carotenoid profiles were provided by the Ohio State University Tomato Breeding and Genetics program and Lipman Family Farms (Naples, FL, USA). Non-destructive measurement from the surface of tomatoes was performed by a handheld Raman spectrometer equipped with a 1064 nm excitation laser, and data analysis was performed using soft independent modelling of class analogy (SIMCA)), artificial neural network (ANN), and partial least squares regression (PLSR) for classification and quantification purposes. High-performance liquid chromatography (HPLC) and UV/visible spectrophotometry were used for profiling and quantification of major carotenoids. Seven groups were identified based on their carotenoid profile, and supervised classification by SIMCA and ANN clustered samples with 93% and 100% accuracy based on a validation test data, respectively. All-trans-lycopene and β-carotene levels were measured with a UV-visible spectrophotometer, and prediction models were developed using PLSR and ANN. Regression models developed with Raman spectra provided excellent prediction performance by ANN (rpre = 0.9, SEP = 1.1 mg/100 g) and PLSR (rpre = 0.87, SEP = 2.4 mg/100 g) for non-invasive determination of all-trans-lycopene in fruits. Although the number of samples were limited for β-carotene quantification, PLSR modeling showed promising results (rcv = 0.99, SECV = 0.28 mg/100 g). Non-destructive evaluation of tomato carotenoids can be useful for tomato breeders as a simple and rapid tool for developing new varieties with novel profiles and for separating orange varieties with distinct carotenoids (high in β-carotene and high in cis-lycopene).

  • 
  AtıfScopus40·WoS32·OpenAlex48

  İncele