WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7150
Browse
12 results
Search Results
Article Citation - WoS: 4Citation - Scopus: 4A New Shapley-Based Feature Selection Method in a Clinical Decision Support System for the Identification of Lung Diseases(MDPI, 2023) Kababulut, Fevzi Yasin; Kuntalp, Damla Gurkan; Düzyel, Okan; Özcan, Nermin; Kuntalp, MehmetThe aim of this study is to propose a new feature selection method based on the class-based contribution of Shapley values. For this purpose, a clinical decision support system was developed to assist doctors in their diagnosis of lung diseases from lung sounds. The developed systems, which are based on the Decision Tree Algorithm (DTA), create a classification for five different cases: healthy and disease (URTI, COPD, Pneumonia, and Bronchiolitis) states. The most important reason for using a Decision Tree Classifier instead of other high-performance classifiers such as CNN and RNN is that the class contributions of Shapley values can be seen with this classifier. The systems developed consist of either a single DTA classifier or five parallel DTA classifiers each of which is optimized to make a binary classification such as healthy vs. others, COPD vs. Others, etc. Feature sets based on Power Spectral Density (PSD), Mel Frequency Cepstral Coefficients (MFCC), and statistical characteristics extracted from lung sound recordings were used in these classifications. The results indicate that employing features selected based on the class-based contribution of Shapley values, along with utilizing an ensemble (parallel) system, leads to improved classification performance compared to performances using either raw features alone or traditional use of Shapley values.Conference Object Citation - Scopus: 2Parkinson hastalığı sınıflandırmasına yönelik ivmeölçer tabanlı zamanlama analizi(IEEE, 2023) Karaçalı, Bilge; Onay, FatihParkinson's disease is a neurodegenerative disorder caused by dopamine deficiency in the basal ganglia, resulting in cognitive and motor impairments. In this study, accelerometer signals were used to estimate the delay time between the command to start pedaling and the actual movement onset in three groups: healthy individuals (n=13), Parkinson's disease patients (n=13), and patients with freezing of gait symptoms (n=13). Features were extracted from the delay time distributions for each participant and subjected to a triple classification. Linear support vector machine achieved a classification accuracy of 69.2% for all participants. Notably, the average time to start pedaling was found to be significantly different among the three groups, and accelerometer-based timing analysis could be used as a diagnostic tool to assist clinical tests.Article Citation - WoS: 11Citation - Scopus: 11The Utilization of Supervised Classification Sampling for Environmental Monitoring in Turin (italy)(MDPI, 2021) Salata, StefanoIn a world threatened by climate change, the need to observe the land transformation is crucial to set environmental policies. One of the most prominent issues of environmental monitoring is the availability of updated and reliable land use data. The last land-use release in Piedmont Region (Italy) is in 2010, while the most updated Normalized Difference Vegetation Index is in 2016. To overcome this limit, in this study, a supervised classification sampling has been applied on a Sentinel-2 image produced by the Copernicus Program on 29 September 2020, using Esri ArcGIS (ver.10.8 Redlands, California, US) by accessing via ONDA-DIAS services to L2A products. After land classification, three maps were generated-the Habitat Quality, the Habitat Decay, and the Normalized Difference Vegetation Index. This study aimed at classifying the environmental status in five classes ranging from critical to health with a double perspective-(i) to make a comparative metropolitan assessment between municipalities and (ii) to evaluate the quality of urban public green areas in the city of Turin while defining a different kind of intervention. Results indicate that products derived from supervised classification sampling can be applied in a wide range of applications while reaching seasonal monitoring of the environmental status and delivering just-in-time solutions.Article Citation - WoS: 42Citation - Scopus: 47Effects of Malaxation Temperature and Harvest Time on the Chemical Characteristics of Olive Oils(Elsevier Ltd., 2016) Jolayemi, Olusola Samuel; Tokatlı, Figen; Özen, BanuThe aim of the study was to determine the effects of harvest time and malaxation temperature on chemical composition of olive oils produced from economically important olive varieties with a full factorial experimental design. The oils of Ayvalik and Memecik olives were extracted in an industrial two-phase continuous system. The quality parameters, phenolic and fatty acid profiles were determined. Harvest time, olive variety and their interaction were the most significant factors. Malaxation temperature was significant for hydroxytyrosol, tyrosol, p-coumaric acid, pinoresinol and peroxide value. Early and mid-harvest oils had high hydroxytyrosol and tyrosol (maximum 20.7 mg/kg) and pigment concentrations (maximum chlorophyll and carotenoids as 4.6 mg/kg and 2.86 mg/kg, respectively). Late harvest oils were characterized with high peroxide values (9.2-25 meq O2/kg), stearic (2.4-3.1%) and linoleic acids (9.3-10.4%). Multivariate regression analysis showed that oxidative stability was affected positively by hydroxytyrosol, tyrosol and oleic acid and negatively by polyunsaturated fatty acids.Article Citation - WoS: 14Citation - Scopus: 12The Impact of Feature Selection on One and Two-Class Classification Performance for Plant Micrornas(PeerJ Inc., 2016) Khalifa, Waleed; Yousef, Malik; Saçar Demirci, Müşerref Duygu; Allmer, JensMicroRNAs (miRNAs) are short nucleotide sequences that form a typical hairpin structure which is recognized by a complex enzyme machinery. It ultimately leads to the incorporation of 18-24 nt long mature miRNAs into RISC where they act as recognition keys to aid in regulation of target mRNAs. It is involved to determine miRNAs experimentally and, therefore, machine learning is used to complement such endeavors. The success of machine learning mostly depends on proper input data and appropriate features for parameterization of the data. Although, in general, two-class classification (TCC) is used in the field; because negative examples are hard to come by, one-class classification (OCC) has been tried for pre-miRNA detection. Since both positive and negative examples are currently somewhat limited, feature selection can prove to be vital for furthering the field of pre-miRNA detection. In this study, we compare the performance of OCC and TCC using eight feature selection methods and seven different plant species providing positive pre-miRNA examples. Feature selection was very successful for OCC where the best feature selection method achieved an average accuracy of 95.6%, thereby being ~29% better than the worst method which achieved 66.9% accuracy. While the performance is comparable to TCC, which performs up to 3% better than OCC, TCC is much less affected by feature selection and its largest performance gap is ~13% which only occurs for two of the feature selection methodologies. We conclude that feature selection is crucially important for OCC and that it can perform on par with TCC given the proper set of features.Book Part Citation - WoS: 299Citation - Scopus: 406Introduction To Machine Learning(Humana Press, 2014) Baştanlar, Yalın; Özuysal, MustafaThe machine learning field, which can be briefly defined as enabling computers make successful predictions using past experiences, has exhibited an impressive development recently with the help of the rapid increase in the storage capacity and processing power of computers. Together with many other disciplines, machine learning methods have been widely employed in bioinformatics. The difficulties and cost of biological analyses have led to the development of sophisticated machine learning approaches for this application area. In this chapter, we first review the fundamental concepts of machine learning such as feature assessment, unsupervised versus supervised learning and types of classification. Then, we point out the main issues of designing machine learning experiments and their performance evaluation. Finally, we introduce some supervised learning methods.Article Citation - WoS: 30Machine Learning Methods for Microrna Gene Prediction(Humana Press, 2014) Saçar, Müşerref Duygu; Allmer, JensMicroRNAs (miRNAs) are single-stranded, small, noncoding RNAs of about 22 nucleotides in length, which control gene expression at the posttranscriptional level through translational inhibition, degradation, adenylation, or destabilization of their target mRNAs. Although hundreds of miRNAs have been identified in various species, many more may still remain unknown. Therefore, discovery of new miRNA genes is an important step for understanding miRNA-mediated posttranscriptional regulation mechanisms. It seems that biological approaches to identify miRNA genes might be limited in their ability to detect rare miRNAs and are further limited to the tissues examined and the developmental stage of the organism under examination. These limitations have led to the development of sophisticated computational approaches attempting to identify possible miRNAs in silico. In this chapter, we discuss computational problems in miRNA prediction studies and review some of the many machine learning methods that have been tried to address the issues.Article Citation - WoS: 23Citation - Scopus: 28Classification of Turkish Monocultivar (ayvalık and Memecik Cv.) Virgin Olive Oils From North and South Zones of Aegean Region Based on Their Triacyglycerol Profiles(John Wiley and Sons Inc., 2013) Gökçebag, Mümtaz; Dıraman, Harun; Özdemir, DurmuşIn this study, a total of 22 domestic monocultivar (AyvalIk and Memecik cv.) virgin olive oil samples taken from various locations of the Aegean region, the main olive growing zone of Turkey, during two (2001-2002) crop years were classified and characterized by well-known chemometric methods (principal component analysis [PCA] and hierarchical cluster analysis [HCA]) on the basis of their triacylglycerol (TAG) components. The analyses of TAG components (LLL and major fractions LOO, OOO, POO, PLO, SOO, and ECN 42-ECN 50) in the oil samples were carried out according to the HPLC method described in a European Union Commission (EUC) regulation. In all analyzed samples the value of trilinolein (LLL), the least abundant TAG, did not exceed the maximum limit of 0.5 % given by the EUC regulation for different olive oil grades. The ranges of abundant TAG, namely LOO, OOO, POO, PLO, and SOO, were 13.30-16.08, 37.27-46.36, 21.39-23.24, 4.93-7.03, and 4.72-6.00 %. The TAG data of Aegean virgin olive oils were similar to those of products from important olive-oil-producing Mediterranean countries was determined. Also, the estimation of major fatty acids (FA) was carried out by using a formula based on TAG data. The PCA results showed that some TAG components have an important role in the characterization and geographical classification of 22 monocultivar virgin olive oil. The Aegean virgin olive oil samples were successfully classified and discriminated into two main groups as the North and South (growing) subzones or AyvalIk and Memecik olives (cultivars) according to the HCA results based on experimental TAG data and calculated major FA profile.Article Citation - WoS: 14Citation - Scopus: 16Classification of Turkish Extra Virgin Olive Oils by a Saw Detector Electronic Nose(John Wiley and Sons Inc., 2011) Kadiroğlu, Pınar; Korel, Figen; Tokatlı, FigenAn electronic nose (e-nose), in combination with chemometrics, has been used to classify the cultivar, harvest year, and geographical origin of economically important Turkish extra virgin olive oils. The aroma fingerprints of the eight different olive oil samples [Memecik (M), Erkence (E), Gemlik (G), Ayvalik (A), Domat (D), Nizip (N), Gemlik-Edremit (GE), Ayvalik-Edremit (AE)] were obtained using an e-nose consisting a surface acoustic wave detector. Data were analyzed by principal component analysis (PCA) and discriminant function analysis (DFA). Classification of cultivars using PCA revealed that A class model was correctly discriminated from N in two harvest years. The DFA classified 100 and 97% of the samples correctly according to the cultivar in the 1st and 2nd harvest years, respectively. Successful separation among the harvest years and geographical origins were obtained. Sensory analyses were performed for determining the differences in the geographical origin of the olive oils and the preferences of the panelists. The panelists could not detect the differences among olive oils from two different regions. The cultivar, harvest year, and geographical origin of extra virgin olive oils could be discriminated successfully by the e-nose.Article Citation - WoS: 6Citation - Scopus: 7Classification of Manipulators of the Same Origin by Virtue of Compactness and Complexity(Elsevier Ltd., 2011) Gezgin, Erkin; Özdemir, SerhanThis work deals with a classification method that employs concepts such as complexity and compactness. The idea is to classify manipulators, or any other mechanism for that matter, of the same origin, based on the geometry of the joints, the tasks performed by the joints, the efficiency and the manufacturing cost to generate the specified efficiency. It is known that successive units on a single branch create individual uncertainties that affect the eventual quality of the performed operation [1]. An entropic expression quantifies this uncertainty in terms of the number of links and the unit effectiveness. The concepts of compactness and complexity have been formulated, and these concepts are explained through serial and parallel manipulators with varying parameters. Eventually, a cost function is created which is a function of complexity, uncertainty and the manufacturing cost. A worked example on M = 6 Stewart-Gough platform is given how this cost function could be taken advantage of when deciding an initial manipulator. A genetic algorithm is used for the optimization of the cost function, where the results are tabulated.