Search results for "convolutional"
showing 10 items of 186 documents
A Comparative Analysis of Residual Block Alternatives for End-to-End Audio Classification
2020
Residual learning is known for being a learning framework that facilitates the training of very deep neural networks. Residual blocks or units are made up of a set of stacked layers, where the inputs are added back to their outputs with the aim of creating identity mappings. In practice, such identity mappings are accomplished by means of the so-called skip or shortcut connections. However, multiple implementation alternatives arise with respect to where such skip connections are applied within the set of stacked layers making up a residual block. While residual networks for image classification using convolutional neural networks (CNNs) have been widely discussed in the literature, their a…
Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment
2021
[EN] Convolutional neural networks (CNNs) are widely used state-of-the-art computer vision tools that are becoming increasingly popular in high-energy physics. In this paper, we attempt to understand the potential of CNNs for event classification in the NEXT experiment, which will search for neutrinoless double-beta decay in Xe-136. To do so, we demonstrate the usage of CNNs for the identification of electron-positron pair production events, which exhibit a topology similar to that of a neutrinoless double-beta decay event. These events were produced in the NEXT-White high-pressure xenon TPC using 2.6 MeV gamma rays from a Th-228 calibration source. We train a network on Monte Carlo-simulat…
Differentiating Malignant from Benign Pigmented or Non-Pigmented Skin Tumours—A Pilot Study on 3D Hyperspectral Imaging of Complex Skin Surfaces and …
2022
Several optical imaging techniques have been developed to ease the burden of skin cancer disease on our health care system. Hyperspectral images can be used to identify biological tissues by their diffuse reflected spectra. In this second part of a three-phase pilot study, we used a novel hand-held SICSURFIS Spectral Imager with an adaptable field of view and target-wise selectable wavelength channels to provide detailed spectral and spatial data for lesions on complex surfaces. The hyperspectral images (33 wavelengths, 477–891 nm) provided photometric data through individually controlled illumination modules, enabling convolutional networks to utilise spectral, spatial, and skin-surface mo…
Emergency Analysis: Multitask Learning with Deep Convolutional Neural Networks for Fire Emergency Scene Parsing
2021
In this paper, we introduce a novel application of using scene semantic image segmentation for fire emergency situation analysis. To analyse a fire emergency scene, we propose to use deep convolutional image segmentation networks to identify and classify objects in a scene based on their build material and their vulnerability to catch fire. We introduce our own fire emergency scene segmentation dataset for this purpose. It consists of real world images with objects annotated on the basis of their build material. We use state-of-the-art segmentation models: DeepLabv3, DeepLabv3+, PSPNet, FCN, SegNet and UNet to compare and evaluate their performance on the fire emergency scene parsing task. …
Fingerprint classification based on deep learning approaches: Experimental findings and comparisons
2021
Biometric classification plays a key role in fingerprint characterization, especially in the identification process. In fact, reducing the number of comparisons in biometric recognition systems is essential when dealing with large-scale databases. The classification of fingerprints aims to achieve this target by splitting fingerprints into different categories. The general approach of fingerprint classification requires pre-processing techniques that are usually computationally expensive. Deep Learning is emerging as the leading field that has been successfully applied to many areas, such as image processing. This work shows the performance of pre-trained Convolutional Neural Networks (CNNs…
Approximate quantum error correction for generalized amplitude damping errors
2014
We present analytic estimates of the performances of various approximate quantum error correction schemes for the generalized amplitude damping (GAD) qubit channel. Specifically, we consider both stabilizer and nonadditive quantum codes. The performance of such error-correcting schemes is quantified by means of the entanglement fidelity as a function of the damping probability and the non-zero environmental temperature. The recovery scheme employed throughout our work applies, in principle, to arbitrary quantum codes and is the analogue of the perfect Knill-Laflamme recovery scheme adapted to the approximate quantum error correction framework for the GAD error model. We also analytically re…
Accumulation of entanglement in a continuous variable memory
2007
We study the accumulation of entanglement in a memory device built out of two continuous variable (CV) systems. We address the case of a qubit mediating an indirect joint interaction between the CV systems. We show that, in striking contrast with respect to registers built out of bidimensional Hilbert spaces, entanglement superior to a single ebit can be efficiently accumulated in the memory, even though no entangled resource is used. We study the protocol in an immediately implementable setup, assessing the effects of the main imperfections.
Quantum error correction against photon loss using NOON states
2015
The so-called NOON states are quantum optical resources known to be useful especially for quantum lithography and metrology. At the same time, they are known to be very sensitive to photon losses and rather hard to produce experimentally. Concerning the former, here we present a scheme where NOON states are the elementary resources for building quantum error correction codes against photon losses, thus demonstrating that such resources can also be useful to suppress the effect of loss. Our NOON-code is an exact code that can be systematically extended from one-photon to higher-number losses. Its loss scaling depending on the codeword photon number is the same as for some existing, exact los…
CNN-based People Detection in Voxel Space using Intensity Measurements and Point Cluster Flattening
2021
In this paper real-time people detection is demonstrated in a relatively large indoor industrial robot cell as well as in an outdoor environment. Six depth sensors mounted at the ceiling are used to generate a merged point cloud of the cell. The merged point cloud is segmented into clusters and flattened into gray-scale 2D images in the xy and xz planes. These images are then used as input to a classifier based on convolutional neural networks (CNNs). The final output is the 3D position (x,y,z) and bounding box representing the human. The system is able to detect and track multiple humans in real-time, both indoors and outdoors. The positional accuracy of the proposed method has been verifi…
Diagonal space time hadamard codes with erasure decoding algorithm
2005
A major challenge in the area of space time (ST) codes is to find codes suitable for efficient decoding, thus overcoming the problem of many existing ST code designs which require maximum-likelihood (ML) decoding. A solution could be to apply single-input single-output (SISO) channel codes and theory over temporal channel fading to the multi-input single-output (MISO) code construction and classical suboptimum decoding methods. For these purposes, an ST code construction which allows the use of efficient decoding algorithms is described. We propose a concatenated code, where the inner code is the diagonal ST Hadamard (D-STH) code with Paley constructions and the outer code is an algebraic b…