Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/11727/4809
Browse
3 results
Search Results
Item Investigation of some machine learning algorithms in fish age classification(2021) Benzer, Semra; Garabaghi, Farid Hassanbaki; Benzer, Recep; Mehr, Homay Danaei; 0000-0002-5339-0554; A-5050-2014Marine and freshwater scientists use fish scales, vertebrae, otoliths and length-weights values to estimate fish age because reliable fish age estimation plays a very important role in fish stock management. The advances in technology and the widespread use of artificial intelligence have revealed the use of traditional observations and techniques in the fishing industry. The aim of this study was to evaluate the effectiveness of three disesteemed machine learning algorithms (NB, J48 DT, RF) in comparison with ANNs which has been widely used in such studies in the literature. In culmination, all three algorithms outperformed ANNs and can be considered as alternatives in case of coming across noisy and non-linear datasets. Moreover, among these three algorithms J48 DT and RF showed exceptional performance where the data for specific fish age groups weren't abundant.Item Can Computerized Adaptive Testing Work in Students' Admission to Higher Education Programs in Turkey?(2017) Berberoglu, Giray; Kalender, IlkerAdmission into university in Turkey is very competitive and features a number of practical problems regarding not only the test administration process itself, but also concerning the psychometric properties of test scores. Computerized adaptive testing (CAT) is seen as a possible alternative approach to solve these problems. In the first phase of the study, a series of CAT simulations based on real students' responses to science items were conducted in order to determine which test termination rule produced more comparable results with scores made on the paper and pencil version of the test. An average of 17 items was used to terminate the CAT administration for a reasonable reliability level as opposed to the normal 45 items. Moreover, CAT based science scores not only produced similar correlations when using mathematics subtest scores as an external criterion, but also ranked the students similarly to the paper and pencil test version. In the second phase, a live CAT administration was implemented using an item bank composed of 242 items with a group of students who had previously taken the exam the paper and pencil version of the test. A correlation of.76 was found between the CAT and paper and pencil scores for this group. The results seem to support the CAT version of the subtests as a feasible alternative approach in Turkey's university admission system.Item Sparsity-driven weighted ensemble classifier(2018) Erdem, Hamit; Ozgur, Atilla; Nar, FatihIn this study, a novel sparsity-driven weighted ensemble classifier (SDWEC) that improves classification accuracy and minimizes the number of classifiers is proposed. Using pre-trained classifiers, an ensemble in which base classifiers votes according to assigned weights is formed. These assigned weights directly affect classifier accuracy. In the proposed method, ensemble weights finding problem is modeled as a cost function with the following terms: (a) a data fidelity term aiming to decrease misclassification rate, (b) a sparsity term aiming to decrease the number of classifiers, and (c) a non-negativity constraint on the weights of the classifiers. As the proposed cost function is non-convex thus hard to solve, convex relaxation techniques and novel approximations are employed to obtain a numerically efficient solution. Sparsity term of cost function allows trade-off between accuracy and testing time when needed. The efficiency of SDWEC was tested on 11 datasets and compared with the state-of-the art classifier ensemble methods. The results show that SDWEC provides better or similar accuracy levels using fewer classifiers and reduces testing time for ensemble.