GCRIS

Now showing 1 - 2 of 2

Ensemble-Based Alzheimer's Disease Classification Using Features Extracted From Hog Descriptor and Pre-Trained Models
(Sakarya University, 2024) Muzoğlu, Nedim; Akbacak, Enver
Alzheimer's Disease is the most common type of dementia and is a progressive, neurodegenerative disease. The disease worsens over time, and the patient becomes bedridden, unable to move or understand what is happening around him. The main concern of medicine is to slow down the progression of the disease for which no treatment has yet been developed. Artificial intelligence studies have achieved significant success in detecting many diseases. In this study, an artificial intelligence-based approach that uses MR images of the early stage of Alzheimer's Disease to detect the disease at an early stage is presented. Initially, a new dataset was created through the application of the fuzzy technique, thereby expanding the feature space. Then, an ensemble learning-based hybrid deep learning model was developed to reduce the misclassification rate for all classes. The features derived from the inception module, residual modules, and histogram of oriented gradients descriptor are subjected to classification through bagging and boosting algorithms. The proposed model has surpassed many state-of-the-art studies by achieving a high success rate of 99.60% in detecting Alzheimer's disease in its early stages.
Speculative Fiction and Pattern Recognition: Narrative Models for a Retrained Intuition
(Rector Ciu Cyprus int Univ, 2023) Ustun, Berkay
The notion of pattern recognition emerged in the late 1950s as an extension of advances in cybernetics and information theory. From the start, authors of science fiction and speculative fiction narratives made their own explorations of the concept, taking it to fields and extremes not predicted by the state of development of pattern recognition technologies. I argue that a pair of these narratives provide opportunities to observe the development of a public understanding of, and imaginaries deriving from, a vision of perception geared toward patterns, arrangements, and configurations that involve historical change. More specifically, these narratives stage questions of historical meaning and intuitive grasp of patterns of consumer behavior by modifying the notion they borrow from computational research through the intermediary of media theory. A second goal of the article is to examine literary history by taking the relevant works of Brunner and Gibson as favorable cases for observing the beginnings and transformations of the reception of pattern recognition concept by speculative fiction. The common reference they make to historical concretion serves as a constant across their differences here. Both fictions seem to stage the possibilities of pattern literacy as a human capacity that includes but is not reducible to one of its most famous and problematic avatars, which is that of a sense of conspiracy, belief gone awry, and/or paranoia (which, according to Fredric Jameson, is the "poor person's cognitive mapping''). Methodologically relying on a combination of media theory and close readings, the goal here is to ascertain whether such fictions constitute viable cases for a "pattern recognition from below", as distinct from a data-intensive pursuit. In this sense, this study neither constitutes an intellectual history of pattern recognition that reduces the object of its study to mere accouterments of context nor simply a close reading of each of the texts on their own terms. It is a comparative exercise that aims to gain surplus of historical and textual intelligibility through the juxtaposition of its chronologically distant narratives. From different angles, the two close readings treat the same core problem of the possibility to retain an affirmative approach to the historical-morphological possibilities inherent in pattern recognition and not consign it to an "ideology" of the information society. Keywords: Concrete, abstract, pattern recognition,

TR-Dizin İndeksli Yayınlar Koleksiyonu

Browse

Filters

Settings

Sort By

Results per page

Search Results