Lung cancer is among the most common and deadliest cancers with a low 5-year survival rate. Timely diagnosis of lung is, therefore, paramount importance as it can save countless lives. In this regard, Computed Tomography (CT) scan widely used for early detection cancer, where human judgment currently considered gold standard approach. Recently, there has been surge interest on development autom...

Deep neural networks based methods dominate recent development in single channel speech enhancement. In this paper, we propose a multi-scale feature recalibration convolutional encoder-decoder with bidirectional gated recurrent unit (BGRU) architecture for end-to-end More specifically, 2-D layers are used to extract local and contextual features from the signal. addition, gating mechanism is ne...

In this paper we make two contributions to unsupervised domain adaptation in the convolutional neural network. First, our approach transfers knowledge in the deep side of neural networks for all convolutional layers. Previous methods usually do so by directly aligning higherlevel representations, e.g., aligning the activations of fullyconnected layers. In this case, although the convolutional l...

We introduce a new method to combine the output probabilities of convolutional neural networks which we call Weighted Convolutional Neural Network Ensemble. Each network has an associated weight that makes networks with better performance have a greater influence at the time to classify in relation to networks that performed worse. This new approach produces better results than the common metho...

Convolutional Neural Networks have recently been shown to be highly effective classifiers for image and speech data. Due to the large volume of data required to build useful models, and the complexity of the models themselves, efficiency has become one of the primary concerns. This work shows that frequency domain methods can be utilised to accelerate the performance training, inference, and sl...

In this paper we present a method for the application of Convolutional Neural Network (CNN) operators for use in domains which exhibit irregular spatial geometry by use of the spectral domain of a graph Laplacian, Figure 1. This allows learning of localized features in irregular domains by defining neighborhood relationships as edge weights between vertices in graph G. By formulating the domain...

In this paper, we propose a novel tensor graph convolutional neural network (TGCNN) to conduct convolution on factorizable graphs, for which here two types of problems are focused, one is sequential dynamic graphs and the other is cross-attribute graphs. Especially, we propose a graph preserving layer to memorize salient nodes of those factorized subgraphs, i.e. cross graph convolution and grap...

Abstract The correct and robust recognition of traffic signs is indispensable to self-driving vehicles driver-assistant systems. In this work, we propose evaluate two network architectures for multi-expert decision systems that test on a challenging Traffic Sign Recognition Benchmark dataset. implement individual experts in the form deep convolutional neural networks (CNNs). A gating CNN acts a...

The Time Projection Chamber (TPC) of the ALICE experiment at CERN LHC was upgraded for Run 3 and 4. Readout chambers based on Gas Electron Multiplier (GEM) technology a new readout scheme allow continuous data taking highest interaction rates expected in Pb-Pb collisions. Due to absence gating grid system, significant amount ions created multiplication region is enter TPC drift volume distort u...

This article presents a multiscale patch based convolutional neural network for the automatic segmentation of brain tumors in multimodality 3D MR images. We use multiscale deep supervision and inputs to train a convolutional network. We evaluate the effectiveness of the proposed approach on the BRATS 2017 segmentation challenge [1, 2, 3, 4] where we obtained dice scores of 0.755, 0.900, 0.782 a...