No abstract

The present study illustrates a convolution neural network designed to classify skin lesion images to benign and malignant melanoma. The convolutional neural network consists of 4 convolution layers, rectified linear activation function and a softmax classifier. The new architecture is experimented to extract features with the following learning methods: Adaptive Moment Estimation and Stochastic Gradient Descent which optimize the weight changing functions for quicker convergence to minimal error between the ground truth and the real output. To further strengthen the accuracy and accelerate the convergence of classification, random noise is added to the neural network learning methods. To validate the theoretical concepts, experiments are conducted with 3800 skin lesion images from the ISIC2018 dataset. At the end of the paper, the results obtained by the convolutional neural network with noisy Stochastic Gradient Descent and noisy Adaptive Moment Estimation are compared with other contemporary classifiers including convolution neural network. Table 3 reports the accuracy of 95.23%, obtained by the new classifier. This value establishes the supremacy of the newly proposed neural network over the other contemporary neural network classifiers.

Interest in neurological disorders has grown exponentially over the last decade with rapidly developing technologies and more refined diagnostics. Epilepsy is the neurological disorders with welllocalized sources of seizures. The understanding of conditions that lead to different types of epileptic seizures of different types, as well as the extent of the damage caused by these seizures is limited. Insight into these issues is especially critical in surgical procedures in cases of epilepsy that are currently nontreatable with medication. In this communication, two models of neuron dynamics (the Kuramoto model and the FitzHugh-Nagumo model) were analyzed. While the FitzHugh-Nagumo network model addresses an ensemble of neurons interacting each other and identifies their synchronic behavior, the Kuramoto model is used to investigate the synchrony between different cortical areas that belong to different brain zones from where EEGs are measured. In both cases, the influence of the connectivity matrix on the dynamical response is studied. Conditions favorable for epileptic seizure were assessed in terms of topological measures of the network. Centrality and clustering values were observed to be the most significant.