Yüsra İnci

Dr. Yüsra İnci

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 August 2024 in Sensors
Verified
Journal Article
Open access
PDF file
YİYüsra İnci
Yüsra İnci
ABAli Volkan BİLGİLİ
Ali Volkan BİLGİLİ
RGRecep Gündoğan
Recep Gündoğan
GGGafur GÖZÜKARA
Gafur GÖZÜKARA
KKKerim KARADAĞ
Kerim KARADAĞ
MTMehmet Emin Tenekeci
Mehmet Emin Tenekeci
In soil science, the allocation of soil samples to their respective origins holds paramount significance, as it serves as a crucial investigative tool. In recent times, with the increasing use of proximal sensing and advancements in machine-learning techniques, new approaches have accompanied these developments, enhancing the effectiveness of soil utilization in soil science. This study investigates soil classification based on four parent materials. For this purpose, a total of 59 soil samples were collected from 12 profiles and the vicinity of each profile at a depth of 0–30 cm. Surface soil samples were analyzed for elemental concentrations using X-Ray fluorescence (XRF) and inductively coupled plasma–optical emission spectrometry (ICP-OES) and soil spectra using a visible near-infrared (Vis-NIR) spectrometer. Soil samples collected from soil profiles (12 soil samples) and surface (47 soil samples) were used to classify parent materials using machine learning-based algorithms such as Support Vector Machine (SVM), Ensemble Subspace k-Near Neighbor (ESKNN), and Ensemble Bagged Trees (EBTs). Additionally, as a validation of the classification techniques, the dataset was subjected to five-fold cross-validation and independent sample set splitting (80% calibration and 20% validation). Evaluation metrics such as accuracy, F score, and G mean were used to evaluate prediction performance. Depending on the dataset and algorithm used, the classification success rates varied between 70% and 100%. Overall, the ESKNN (99%) produced better results than other classification methods. Additionally, Relief algorithms were employed to identify key variables for each dataset (ICP-OES: CaO, Fe2O3, Al2O3, MgO, and MnO; XRF: SiO2, CaO, Fe2O3, Al2O, and MnO; Vis-NIR: 567, 571, 572, 573, and 574 nm). Subsequent soil reclassification using these reduced variables revealed reduced accuracies using Vis-NIR data, with ESKNN still yielding the best results.

25 December 2021 in Harran Tarım ve Gıda Bilimleri Dergisi
Verified
Journal Article
Open access
PDF file
YİYüsra İnci
Yüsra İnci
ABAli Volkan BİLGİLİ
Ali Volkan BİLGİLİ
RGRecep Gündoğan
Recep Gündoğan
Topraklar üzerinde oluştukları ana materyale, iklim koşulları ve topoğrafik yapıya bağlı olarak önemli farklılıklar gösterirler. Adli bilimde de önemli olan bu farklılıkların belirlenmesi daha fazla arazi ve laboratuvar çalışmalarına ihtiyaç duyar bu da daha fazla iş gücü, kimyasal kullanımı ve zaman gerektirir. Öteki taraftan Görülebilir ve Yakın Kızılötesi Spektroradyometre (VNIRS) Tekniği gibi yaklaşımlar toprakların hızlıca ve birden fazla toprak özelliğinin eş zamanlı olarak karakterizasyonunda son zamanlarda yaygın bir şekilde kullanılmaya başlanmıştır. Toprak örneklerinin tahribatsız analiz edilmesine izin veren bu yöntem; orijinal örneklerin korunmasının büyük önem taşıdığı adli kullanımlar için büyük potansiyele sahiptir. 2019-2020 yılları arasında yürütülen bu çalışmada Çamur akıntıları, Kireçtaşı, Marn ve Bazalt olmak üzere Şanlıurfa’da yaygın dört farklı ana materyal üzerinde oluşmuş toprak profillerden horizon esasına göre alınan 59 toprak örneği; laboratuvar ortamında rutin fiziko kimyasal analizleri yapılmış ve 350-2500 nm dalga boyu aralığında spektral yansımaları elde edilerek Temel Bileşenler Analizi (PCA), Cluster analizi ve Kısmi En Küçük Karaler Regresyon Yöntemi (PLSR)gibi çok değişkenli istatistiksel metotlara tabi tutulmuştur. PLSR modelleri kullanarak toprak parametrelerinin tahmin edilebilirlik başarısıçapraz doğrulama (crossvalidation) yaklaşımı ile test edilmiştir. PC1 ve PC2 toprakların yansımalarındaki değişimin % 99’ undan fazlasını açıklamış ve farklı ana meteryal üzerinde oluşmuş farklı toprakları spektral özelliklerine göre gruplandırabilmiştir. PCA analizi uygulanmış ham toprak yansımalarını kullanan Kümeleme analizi toprakları %61 başarı (Kappa istatistik = 0.62) ile geldikleri ana metaryal türüne göre sınıflandırabilmiştir. Çapraz doğrulama sonuçlarına göre CaCO3 (R2 =0.75, RPD=1.99), kil (R2= 0.72, RPD=1.87), Fe (R2=0.66, RPD=1.72), Al (R2=0.64, RPD=1.64), değişebilir Ca (R2= 0.73, RPD= 2.03), Na (R2=0.65, RPD= 1.71) ve Mg (R2=0.59, RPD= 1.55) gibi parametreler spektral yansımalara bağlı olarak orta seviyede başarılı bir şekilde tahmin edilebilmiştir.

7 March 2026 in Journal of Food Measurement and Characterization
Verified
Journal Article
Open access
PDF file
RURufaioğlu
Rufaioğlu
SRSüreyya Betül Rufaioğlu
Süreyya Betül Rufaioğlu
ABAli Volkan BİLGİLİ
Ali Volkan BİLGİLİ
AIAmjad Mohammed ISMAEL
Amjad Mohammed ISMAEL
YİYüsra İnci
Yüsra İnci
Accurate and non-destructive estimation of wheat protein content is critical for quality-based grain management, precision agriculture, and food industry applications. This study evaluates the performance of traditional and advanced machine learning approaches for predicting wheat flour protein content using spectroradiometric reflectance data across the 350–2500 nm range. Partial Least Squares Regression (PLSR), Random Forest (RF), Deep Learning (DL), and a hybrid Artificial Neural Network–Support Vector Regression (ANN–SVR) model were systematically compared using region-specific spectral subsets, including the visible (VIS: 350–700 nm), near-infrared (NIR: 700–1250 nm), short-wave infrared (SWIR: 1250–2500 nm), and the full spectrum. The results revealed clear performance differences among modeling approaches. PLSR showed limited predictive capability across all spectral regions, indicating its restricted ability to capture non-linear relationships in high-dimensional spectral data. RF models provided improved accuracy by exploiting ensemble learning and feature selection mechanisms, although their performance varied depending on spectral domain. The highest and most stable prediction accuracy was achieved by the ANN–SVR hybrid and deep learning models, which effectively modeled complex non-linear interactions between protein content and spectral reflectance. Among spectral domains, NIR and SWIR regions exhibited strong sensitivity to protein-related absorption features, while the full-spectrum models consistently delivered the best overall performance by integrating complementary spectral information. Spectral difference analysis and principal component analysis further confirmed that protein-related variability is primarily associated with N–H and C–H overtone absorption bands in the NIR–SWIR transition zones. The findings demonstrate that combining hyperspectral spectroscopy with hybrid and deep learning architectures substantially enhances prediction accuracy compared to conventional linear models. Overall, this study highlights the potential of hyperspectral data-driven artificial intelligence models as a rapid, non-destructive, and scalable alternative to conventional laboratory protein analysis. The proposed framework supports real-time quality monitoring, site-specific nitrogen management, and post-harvest grain classification, contributing to sustainable agricultural practices and digital transformation in wheat quality assessment.

23 June 2023 in Harran Tarım ve Gıda Bilimleri Dergisi
Verified
Journal Article
Open access
PDF file
YİYüsra İnci
Yüsra İnci
ABAli Volkan BİLGİLİ
Ali Volkan BİLGİLİ
RGRecep Gündoğan
Recep Gündoğan
YKYusuf Kagan Kadioğlu
Yusuf Kagan Kadioğlu
The use of different instrumental methods as an alternative to traditional methods has become an important issue in order to detect soil change accurately, quickly and economically. In this study, soil profiles formed over four common parent materials (Mudflow, Basalt, Limestone and Marl) in Sanliurfa province of Turkey were described. Soil samples were collected from each horizon, in addition, surface soil samples (0-20 cm) of cultivated and uncultivated lands around the soil profiles were collected. Soil samples were analyzed using instrumental (ICP, XRF) techniques to determine total element (Si, Al, Fe, Ca, Mg, K, P, Mn, Cr) concentrations as oxides, and assess the impact of parent materials and tillage (cultivated vs uncultivated) on the elemental composition. The highest percent total oxides in the soils were SiO2, CaO, AlO2, and MgO. The total oxide concentrations determined by both techniques were close to each other except SiO2, they were statistically different. In general, differences in the mean total oxide values of the investigated elements among the soils formed on different parent materials determined by both methods were found to be statistically significant (p < 0.05) while the effect of soil tillage was significant (p < 0.05) only for the results obtained with the XRF. The impacts of soil tillage status on other elements were statistically negligible (p>0.05), but only MgO was shown to be significantly affected. The percent SiO2 values obtained by the ICP technique were quite low compared to the values obtained by the XRF technique. Overall, in terms of total elemental oxide values obtained, the XRF method was considered more advantageous over the ICP technique as it provides more accurate results and requires less soil samples.

19 May 2026 in Research in Agricultural Sciences
Verified
Journal Article
Open access
NGNecmettin Gür
Necmettin Gür
ÖKÖzgür Kahraman
Özgür Kahraman
YİYüsra İnci
Yüsra İnci
Ornamental plants play a crucial role in urban landscapes due to their aesthetic and ecological value. Improving germination and early seedling development is essential for high-quality ornamental plant production. This study investigated the effects of different salicylic acid (SA) concentrations (0.00, 0.25, 0.50, 0.75, and 1.00 mM) on the germination and early seedling growth of Mirabilis jalapa L. under controlled greenhouse conditions. The results indicated that, among the tested concentrations, 0.25 mM SA increased the germination rate by 11.10% compared to the control group, and improved plant height, leaf number, and root length by 7.70%, 7.44%, and 11.49%, respectively. In contrast, higher concentrations (0.50, 0.75, and 1.00 mM) inhibited the growth parameters. Germination time was not significantly affected by SA treatments. These findings suggest that low-dose SA applications may positively influence early seedling vigor and growth performance, which can indirectly contribute to ornamental plant quality. This study provides baseline data for the potential use of SA in ornamental horticulture and highlights the need for further research on different species and environmental conditions.

1 July 2026 in Earth Science Informatics
Verified
Journal Article
Closed access
PDF file
YİYüsra İnci
Yüsra İnci
MKMiraç Kılıç
Miraç Kılıç
ABAli Volkan Bilgili
Ali Volkan Bilgili
SRSüreyya Betül Rufaioğlu
Süreyya Betül Rufaioğlu
RGRecep Gündoğan
Recep Gündoğan