Yazar "Kavdir, I." seçeneğine göre listele
Listeleniyor 1 - 6 / 6
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Apple Sorting Using Artificial Neural Networks and Spectral Imaging(2002) Kavdir, I.; Guyer, D.E.Empire and Golden Delicious apples were sorted based on their surface quality conditions using backpropagation neural networks. Pixel gray values and texture features obtained from the entire apple image were used as input to artificial neural network classifiers. Two classification applications were performed: a 2-class classification that included a defective (or stem/calyx) apple group and a good apple group, and a 5-class classification that included all the defective and good apple groups. Effective image resolution was evaluated to shorten the training and testing times in classification with neural networks. Resolution size of 60 x 80 pixels was identified to be efficient and used in all of the classification applications. Effective spectral bands for identification of specific surface characteristics were determined in the 2-class and 5-class classification applications. Artificial neural network classifiers successfully separated apples with defects from non-defective apples without confusing the stem/calyx with defects. Classification success in the 2-class classification ranged from 89.2% to 100%. In the 5-class classification, classification success for Empire apples was between 93.8% and 100%, while classification success for Golden Delicious apples was between 89.7% and 94.9% based on the features used.Öğe Evaluation of different pattern recognition techniques for apple sorting(Academic Press Inc Elsevier Science, 2008) Kavdir, I.; Guyer, D. E.Golden Delicious apples were classified using parametric and non-parametric classifiers into three quality classes. The features used in classification of apples were hue angle (for colour), shape defect, circumference, firmness, weight, blush percentage (red natural spots on the surface of the apple), russet (natural netlike formation on the surface of an apple), bruise content and number of natural defects. Different feature sets including four, five and nine features were also tested to find out the best classifier and feature set combination for an optimal classification success. The effects of using different feature sets and classifiers on classification performance were investigated. The feature set including five features produced slightly better classification results in general compared to feature sets including four and nine features. When the classifiers were compared, it was determined that the multi-layer perceptron neural network produced the highest classification results (up to 90%) while 1 - nearest- neighbour and 2-nearest-neighbour classifiers followed this classifier with an 81.11% classification success. The 3-nearest-neighbour and decision tree classifiers resulted in similar classification success (75.56%). The parametric plug-in decision rule classification resulted in the lowest classification success. Principal component analysis and linear discriminant analysis techniques were applied on the training data with nine, five and four features to visualise the degree of separation of the three quality classes of apples. As a result of this application, some improvements were observed in separation of the three quality classes from using four input features to nine features especially using principal components although some overlaps still existed among the classes. (C) 2007 IAgrE. Published by Elsevier Ltd. All rights reserved.Öğe Monitoring composting process of olive oil solid waste using FT-NIR spectroscopy(Taylor & Francis Inc, 2020) Kavdir, Y.; Ilay, R.; Camci Cetin, S.; Buyukcan, M. B.; Kavdir, I.FT-NIR (Fourier Transform-Near Infrared) spectroscopy has been used for the prediction of properties of various materials. Olive oil solid waste compost (OSWC) can be a good and available source for soil organic matter in Mediterranean countries. This study was aimed at developing a fast and nondestructive method for determining compost carbon to nitrogen (C/N) ratio, total nitrogen (TN), inorganic nitrogen, total carbon (C), pH and electrical conductivity (EC) using FT-NIR spectroscopy. Composts were sampled weekly and some chemical analyses were performed on the samples using standard methods. Also, reflectance spectra of the same compost were acquired using FT-NIR spectroscopy right after the standard measurements. Organic matter functional groups of OSW and OSWC were compared using C-13-NMR spectroscopy. Calibration models between the standard measurements and the spectral measurements performed on samples were established applying Partial Least Squares (PLS) method. According to prediction models following determination coefficients (R-2) of 0.86, 0.82, 0.81, 0.77, 0.75, 0.65 and 0.51 were obtained respectively for nitrate (NO3-), pH, ammonium (NH4+), total N, C/N ratio, total C and EC. With this study, it was shown that FT-NIR spectroscopy has the potential of sensing OSWC parameters nondestructively.Öğe Nondestructive Olive Quality Detection Using FT-NIR Spectroscopy in Reflectance Mode(Int Soc Horticultural Science, 2009) Kavdir, I.; Buyukcan, M. B.; Kocabiyik, H.; Lu, R.; Seker, M.Quality features including firmness, oil content, and color (chroma, hue) of two olive (Olea europaea L.) varieties ('Ayvalik' and 'Gemlik') were predicted using FT-NIR spectroscopy. Reflectance measurements of intact olives were performed using a bifurcated fiber optic probe. Measurements of firmness, oil content, and color values were done following the spectral measurements using standard methods. Calibration methods were developed using the partial least squares method. Good correlations were obtained in calibration and validation for Magness-Taylor (MT) maximum force, which was used as a measure of firmness, for both 'Ayvalik' and 'Gemlik' varieties; the coefficient of determination (R-2) for 'Gemlik' olives was 0.74 (SEC = 1.27) in calibration and 0.67 (SEP = 1.37) in validation. Better oil content prediction of olive fruits was obtained for the pooled data of 'Ayvalik' and 'Gemlik' varieties with the R-2 value of 0.64 (SEP = 0.05) in validation. Higher correlations were obtained for color predictions with R-2 = 0.88 and SEP = 12.9 for chroma and R-2 = 0.86 and SEP = 0.10 for hue for 'Gemlik'. Similar color prediction results were obtained for the 'Ayvalik' variety.Öğe Using Chlorophyll Meter to Predict Sunflower Nitrogen Content after Olive Solid Waste Applications(Int Soc Horticultural Science, 2009) Kavdir, Y.; Ilay, R.; Turhan, H.; Genc, L.; Kavdir, I.; Sumer, A.Chlorophyll index is an instantaneous measurement of leaf greenness without the destruction of the plant and a new tool to determine plant nitrogen content and associated yield. A pot experiment was conducted under controlled conditions. Olive solid wastes were mixed with soil at the rates of 0, 3, 5 and 7% with and without additional nitrogen and phosphorous sources. Sunflower was grown in pots for two months. Plant length, leaf number, stem thickness, and chlorophyll meter readings were performed weekly. Plant nitrogen contents and plant weights were determined at harvest. Chlorophyll index and plant nitrogen contents were significantly related (r(2) = 0.86) at the V12 stage. The correlations between chlorophyll meter reading and plant biomass was 0.87 while plant N and plant biomass was 0.96. On the other hand, chlorophyll meter estimation of plant N contents in early stages (V2 and V4) of sunflower growth was not statistically significant. Additions of olive solid waste in the soil reduced chlorophyll meter readings and sunflower biomass.Öğe Visible and near-infrared spectroscopy for nondestructive quality assessment of pickling cucumbers(Elsevier, 2007) Kavdir, I.; Lu, R.; Ariana, D.; Ngouajio, A.This study was aimed at developing a nondestructive method for measuring the firmness, skin and flesh color, and dry matter content of pickling cucumbers by means of visible and near-infrared (Vis/NIR) spectroscopy. 'Journey' and 'Vlaspik' pickling cucumbers were hand harvested and then stored at 10 degrees C and 95% relative humidity for various periods up to 18 days. Spectroscopic measurements were made from each intact cucumber in interactance mode with a low-cost CCD-based Vis/NIR spectrometer over 550-1100 nm and an InGaAs-based NIR spectrometer over 800-1650 run. Standard methods were used to measure skin and flesh color, firmness, and dry matter content of the pickling cucumbers. Calibration models were developed using the partial least squares method for predicting firmness, skin and flesh chroma and hue, and dry matter content. NIR measurements correlated well with Magness-Taylor slope or area, with values for the coefficient of determination (R-2) of 0.70-0.73 for calibration and 0.67-0.70 for validation, better than those obtained with the Vis/NTR spectrometer. Vis/NIR measurements had good correlations with skin chroma (R-2 = 0.89 and 0.83 for calibration and validation, respectively) and hue (R-2 = 0.76 for calibration and validation). Promising results were obtained in predicting dry matter content of the cucumbers with R-2 = 0.65 in validation for 'Journey' cucumbers. Visible and NIR spectroscopy is potentially useful for sorting and grading pickling cucumbers. (c) 2007 Elsevier B.V. All rights reserved.
