5 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 5 / 5
Yayın Texture recognition for frog identification(ACM SIGMM, 2012-11-02) Cannavo, Flavio; Nunnari, Giuseppe; Kale, İzzet; Tek, Faik BorayThis paper describes a visual processing technique for automatic frog (Xenopus Laevis sp.) localization and identification. The problem of frog identification is to process and classify an unknown frog image to determine the identity which is recorded previously on an image database. The frog skin pattern (i.e. texture) provides a unique feature for identification. Hence, the study investigates three different kind of features (i.e. Gabor filters, granulometry, threshold set compactness) to extract texture information. The classifier is built on nearest neighbor principle; it assigns the query feature to the database feature which has the minimum distance. Hence, the study investigates different distance measures and compares their performance. The detailed results show that the most successful feature and distance measure is granulometry and weighted L1 norm for the frog identification using skin texture features.Yayın Convolutional attention network for MRI-based Alzheimer's disease classification and its interpretability analysis(IEEE, 2021-09-17) Türkan, Yasemin; Tek, Faik BorayNeuroimaging techniques, such as Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET), help to identify Alzheimer's disease (AD). These techniques generate large-scale, high-dimensional, multimodal neuroimaging data, which is time-consuming and difficult to interpret and classify. Therefore, interest in deep learning approaches for the classification of 3D structural MRI brain scans has grown rapidly. In this research study, we improved the 3D VGG model proposed by Korolev et al. [2]. We increased the filters in the 3D convolutional layers and then added an attention mechanism for better classification. We compared the performance of the proposed approaches for the classification of Alzheimer's disease versus mild cognitive impairments and normal cohorts on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. We observed that both the accuracy and area under curve results improved with the proposed models. However, deep neural networks are black boxes that produce predictions that require further explanation for medical usage. We compared the 3D-data interpretation capabilities of the proposed models using four different interpretability methods: Occlusion, 3D Ultrametric Contour Map, 3D Gradient-Weighted Class Activation Mapping, and SHapley Additive explanations (SHAP). We observed that explanation results differed in different network models and data classes.Yayın Adaptive convolution kernel for artificial neural networks(Academic Press Inc., 2021-02) Tek, Faik Boray; Çam, İlker; Karlı, DenizMany deep neural networks are built by using stacked convolutional layers of fixed and single size (often 3 × 3) kernels. This paper describes a method for learning the size of convolutional kernels to provide varying size kernels in a single layer. The method utilizes a differentiable, and therefore backpropagation-trainable Gaussian envelope which can grow or shrink in a base grid. Our experiments compared the proposed adaptive layers to ordinary convolution layers in a simple two-layer network, a deeper residual network, and a U-Net architecture. The results in the popular image classification datasets such as MNIST, MNIST-CLUTTERED, CIFAR-10, Fashion, and ‘‘Faces in the Wild’’ showed that the adaptive kernels can provide statistically significant improvements on ordinary convolution kernels. A segmentation experiment in the Oxford-Pets dataset demonstrated that replacing ordinary convolution layers in a U-shaped network with 7 × 7 adaptive layers can improve its learning performance and ability to generalize.Yayın Tweet sentiment analysis for cryptocurrencies(IEEE, 2021-10-13) Şaşmaz, Emre; Tek, Faik BorayMany traders believe in and use Twitter tweets to guide their daily cryptocurrency trading. In this project, we investigated the feasibility of automated sentiment analysis for cryptocurrencies. For the study, we targeted one cryptocurrency (NEO) altcoin and collected related data. The data collection and cleaning were essential components of the study. First, the last five years of daily tweets with NEO hashtags were obtained from Twitter. The collected tweets were then filtered to contain or mention only NEO. We manually tagged a subset of the tweets with positive, negative, and neutral sentiment labels. We trained and tested a Random Forest classifier on the labeled data where the test set accuracy reached 77%. In the second phase of the study, we investigated whether the daily sentiment of the tweets was correlated with the NEO price. We found positive correlations between the number of tweets and the daily prices, and between the prices of different crypto coins. We share the data publicly.Yayın An adaptive locally connected neuron model: Focusing neuron(Elsevier B.V., 2021-01-02) Tek, Faik BorayThis paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The experiments include tests of focusing neuron networks of one or two hidden layers on synthetic and well-known image recognition data sets. The results demonstrated that the focusing neurons can move their receptive fields towards more informative inputs. In the simple two-hidden layer networks, the focusing layers outperformed the dense layers in the classification of the 2D spatial data sets. Moreover, the focusing networks performed better than the dense networks even when 70% of the weights were pruned. The tests on convolutional networks revealed that using focusing layers instead of dense layers for the classification of convolutional features may work better in some data sets.
