3 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 3 / 3
Yayın The composition of acids in bitumen and in products from saponification of kerogen: Investigation of their role as connecting kerogen and mineral matrix(Elsevier Science BV, 2008-11-03) Razvigorova, Maria; Budinova, Temenuzhka K.; Tsyntsarski, Boyko G.; Petrova, Bilyana N.; Ekinci, Ekrem; Atakül, HüsnüIn order to obtain more information and to understand the nature of relation between organic and mineral matter in oil shales, the compositions of soluble bitumen fractions obtained by extraction from Bulgarian oil shales before and after demineralization with 10% HCl, concentrated HE and a HF/HCl mixture were investigated. The four extracts were quantitatively examined by IR and H-1 NMR spectroscopy. The investigation of isolated acidic material of the bitumen fractions showed that the fatty acids are present in bitumen fractions as free acids, esters and salts. The amount of free acids in bitumen is very small. The dominant part of bitumen acids is associated with mineral components of the oil shales as well as part of them is included in the mineral matrix, and can be separated only after deep demineralization. The kerogen of the oil shales, obtained after separation of the bitumen fractions and mineral components, was subjected to saponification in order to determine the amount of acids, bound as esters to the kerogen matrix. The major components found were n-carboxylic, alpha,omega,-di-carboxylic, and aromatic acids. The connection of kerogen with mineral components is accomplished by the participation of carboxylic and complicated ester bonds. Experimental data for the composition of bitumen acids give evidence that algae and terrestrial materials are initial sources in the formation of soluble organic matter of Bulgarian oil shale.Yayın Unsupervised textile defect detection using convolutional neural networks(Elsevier Ltd, 2021-12) Koulali, Imane; Eskil, Mustafa TanerIn this study, we propose a novel motif-based approach for unsupervised textile anomaly detection that combines the benefits of traditional convolutional neural networks with those of an unsupervised learning paradigm. It consists of five main steps: preprocessing, automatic pattern period extraction, patch extraction, features selection and anomaly detection. This proposed approach uses a new dynamic and heuristic method for feature selection which avoids the drawbacks of initialization of the number of filters (neurons) and their weights, and those of the backpropagation mechanism such as the vanishing gradients, which are common practice in the state-of-the-art methods. The design and training of the network are performed in a dynamic and input domain-based manner and, thus, no ad-hoc configurations are required. Before building the model, only the number of layers and the stride are defined. We do not initialize the weights randomly nor do we define the filter size or number of filters as conventionally done in CNN-based approaches. This reduces effort and time spent on hyper-parameter initialization and fine-tuning. Only one defect-free sample is required for training and no further labeled data is needed. The trained network is then used to detect anomalies on defective fabric samples. We demonstrate the effectiveness of our approach on the Patterned Fabrics benchmark dataset. Our algorithm yields reliable and competitive results (on recall, precision, accuracy and f1-measure) compared to state-of-the-art unsupervised approaches, in less time, with efficient training in a single epoch and a lower computational cost.Yayın A novel similarity based unsupervised technique for training convolutional filters(IEEE, 2023-05-17) Erkoç, Tuğba; Eskil, Mustata TanerAchieving satisfactory results with Convolutional Neural Networks (CNNs) depends on how effectively the filters are trained. Conventionally, an appropriate number of filters is carefully selected, the filters are initialized with a proper initialization method and trained with backpropagation over several epochs. This training scheme requires a large labeled dataset, which is costly and time-consuming to obtain. In this study, we propose an unsupervised approach that extracts convolutional filters from a given dataset in a self-organized manner by processing the training set only once without using backpropagation training. The proposed method allows for the extraction of filters from a given dataset in the absence of labels. In contrast to previous studies, we no longer need to select the best number of filters and a suitable filter weight initialization scheme. Applying this method to the MNIST, EMNIST-Digits, Kuzushiji-MNIST, and Fashion-MNIST datasets yields high test performances of 99.19%, 99.39%, 95.03%, and 90.11%, respectively, without applying backpropagation training or using any preprocessed and augmented data.
