Browsing by Author "Fidan, M"

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    Neural network representations for the inter- and intra-class common vector classifiers
    Edizkan, R; Barkana, A; Koc, M; Gulmezoglu, MB; Ashames, MMA; Ergin, S; Fidan, M; Demir, A; Calisir, C; Gerek, ON
    Common Vector Approach (CVA) is a known linear regression-based classifier, which also enables an extension to inter-class discrimination, known as the Discriminative Common Vector Approach (DCVA). The characteristics of linear regression classifiers (LRCs) enable the possibility of a schematic implementation that is similar to the neuron model of artificial neural networks (ANNs). In this work, we explore this schematic similarity to come up with an ANN representation for both CVA and DCVA. The new representation eliminates the need for projection matrices in its implementation, hence significantly reduces the memory requirements and computational complexities of the processes. Furthermore, since the new representation is in a neural style, it is expected to provide a solid and intriguing extension of CVA (and DCVA) by further incorporating adaptation or activation processes to the already successful CVA-based classifiers. (c) 2023 Elsevier Inc. All rights reserved.
  • No Thumbnail Available
    Item
    Are deep learning classification results obtained on CT scans fair and interpretable?
    Ashames, MMA; Demir, A; Gerek, ON; Fidan, M; Gulmezoglu, MB; Ergin, S; Edizkan, R; Koc, M; Barkana, A; Calisir, C
    Following the great success of various deep learning methods in image and object classification, the biomedical image processing society is also overwhelmed with their applications to various automatic diagnosis cases. Unfortunately, most of the deep learning-based classification attempts in the literature solely focus on the aim of extreme accuracy scores, without considering interpretability, or patient-wise separation of training and test data. For example, most lung nodule classification papers using deep learning randomly shuffle data and split it into training, validation, and test sets, causing certain images from the Computed Tomography (CT) scan of a person to be in the training set, while other images of the same person to be in the validation or testing image sets. This can result in reporting misleading accuracy rates and the learning of irrelevant features, ultimately reducing the real-life usability of these models. When the deep neural networks trained on the traditional, unfair data shuffling method are challenged with new patient images, it is observed that the trained models perform poorly. In contrast, deep neural networks trained with strict patient-level separation maintain their accuracy rates even when new patient images are tested. Heat map visualizations of the activations of the deep neural networks trained with strict patient-level separation indicate a higher degree of focus on the relevant nodules. We argue that the research question posed in the title has a positive answer only if the deep neural networks are trained with images of patients that are strictly isolated from the validation and testing patient sets.
  • No Thumbnail Available
    Item
    Use of Digital Mind Maps in Technology Education: A Pilot Study with Pre-Service Science Teachers
    Debbag, M; Cukurbasi, B; Fidan, M
    This case study aims at ensuring preservice science teachers to acquire experience by creating paper-based mind maps (PB-MM) and digital mind maps (D-MM) in technology education and to reveal their opinions on these mind mapping techniques. A total of 32 preservice science teachers, enrolled in the undergraduate program of Science Teaching at a university in Turkey, participated in this study. During the first three weeks of the six-week study, participants created PB-MM for certain subjects in science education. For the rest of the weeks, they created D-MM by using Coggle. As data collection tool, a form, consisting of open-ended questions, was used in this study. The obtained results demonstrated that the participants generally reported positive opinions including that mind maps are beneficial and useful tools in reinforcing, assessing and visualizing learning in general, making lessons more entertaining as well as offering ease of use. It was also concluded that students can also use mind maps in teaching of other topics such as Vitamins, The Earth and the Universe and Systems in particular, as well as in events like meetings, presentations, brainstorming. Advantages of D-MM were listed as the possibility of adding multimedia material, ease of correction processes and the visual richness, while its disadvantage was listed as experiencing technical problems. PB-MM contribute to psychomotor development of students as well as learning by performing/experiencing. The difficulty in processes such as deleting, editing, etc. and in adding videos and images constitute the restrictions of PB-MM technique.
  • No Thumbnail Available
    Item
    Metaphoric perceptions of pre-service teachers about 'LEGO Robotic Instructional Practices,' 'Augmented Reality' and 'Flipped Classroom' concepts
    Fidan, M; Debbag, M; Cukurbasi, B
    The aim of this study is to reveal perceptions of pre-service teachers about 'LEGO robotic instructional practices,' 'augmented reality' and 'flipped classroom' concepts through metaphors. The study is descriptive research that was conducted as a survey model. The study group consists of 37 pre-service teachers studying the undergraduate programme of Science Teaching, Faculty of Education of a university in the Western Black Sea Region in the spring semester of the academic year 2016-2017. A form consisting of three open-ended questions was used as a data collection tool during the study. The data acquired were analyzed through content analysis method. Following the study, 15 different metaphors created in relation to the LEGO robotic instructional practices concept were categorized as 'edutainment tool,' 'a technological tool' and a 'development tool,' while 24 different metaphors created in relation to the augmented reality concept were categorized as 'Perception Of Reality', 'A Technological Tool', 'Change/Transformation Tool' and 'Entertainment Tool'. Moreover, 25 different metaphors created in relation to the flipped classroom concept were classified in two categories as a 'form of education' and 'an education shaping tool'. Moreover, almost all of the metaphors created were observed to have positive features.