Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
2 results
Search Results
Article Citation - Scopus: 2Fatty Acid Alkyl Ester and Wax Compositions of Olive Oils as Varietal Authentication Indicators(Springer, 2022) Uncu, O.; Ozen, B.Minor components of olive oils can be good markers for their authenticity, which is a significant quality issue for this product. It was aimed to determine individual and total fatty acid alkyl esters and waxes as minor constituents of olive oil and to investigate their novel varietal authentication capability separately and in combination for three main olive cultivars grown in three distinct locations of Aegean Region of Turkey. In addition, basic quality and purity parameters as free fatty acid, K values and fatty acid profiles were also determined for the characterization of the samples. Olive oil samples from different cultivars had different fatty acid profiles and two of these varieties had similar quality parameters. Statistical analyses were conducted with orthogonal partial least squares discriminant analysis (OPLS-DA) to differentiate varieties with respect to their individual and combined parameters of fatty acid alkyl esters and waxes. For calibration sets, use of individual fatty acid alkyl esters profile resulted in 80% correct classification rate while waxes alone was 67% successful in classifying the olive oils according to variety. It was found that alkyl esters in combination with waxes were more effective in discrimination of olive oils with respect to cultivar compared to their individual forms and the correct classification rate for the generated model is 92% for calibration set. Since fatty acid alkyl esters along with waxes have effect on cultivar differentiation, they could have a potential as authentication tools for olive oil besides their known quality characteristics. © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Conference Object Citation - WoS: 1Citation - Scopus: 2Fisher's Linear Discriminant Analysis Based Prediction Using Transient Features of Seismic Events in Coal Mines(Institute of Electrical and Electronics Engineers Inc., 2016) Köktürk Güzel, Başak Esin; Karaçalı, BilgeIdentification of seismic activity levels in coal mines is important to avoid accidents such as rockburst. Creating an early warning system that can save lives requires an automated way of predicting. This study proposes a prediction algorithm for the AAIA'16 Data Mining Challenge: Predicting Dangerous Seismic Events in Active Coal Mines that is based on transient activity features along with average indicators evaluated by a Fisher's linear discriminant analysis. Performance evaluation experiments on the training datasets revealed an accuracy level of around 0.9438 while the performance on the test dataset was at a level of 0.9297. These results suggest that the proposed approach achieves high accuracy in predicting danger seismic events while maintaining low complexity.