Search results for "Processing"

Causality-Aware Convolutional Neural Networks for Advanced Image Classification and Generation

2023

Smart manufacturing uses emerging deep learning models, and particularly Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), for different industrial diagnostics tasks, e.g., classification, detection, recognition, prediction, synthetic data generation, security, etc., on the basis of image data. In spite of being efficient for these objectives, the majority of current deep learning models lack interpretability and explainability. They can discover features hidden within input data together with their mutual co-occurrence. However, they are weak at discovering and making explicit hidden causalities between the features, which could be the reason behind the parti…

Novel qutrit circuit design for multiplexer, De-multiplexer, and decoder

2022

AbstractDesigning conventional circuits present many challenges, including minimizing internal power dissipation. An approach to overcoming this problem is utilizing quantum technology, which has attracted significant attention as an alternative to Nanoscale CMOS technology. The reduction of energy dissipation makes quantum circuits an up-and-coming emerging technology. Ternary logic can potentially diminish the quantum circuit width, which is currently a limitation in quantum technologies. Using qutrit instead of qubit could play an essential role in the future of quantum computing. First, we propose two approaches for quantum ternary decoder circuit in this context. Then, we propose a qua…

Controlling Atom-Photon Bound States in an Array of Josephson-Junction Resonators

2022

Engineering the electromagnetic environment of a quantum emitter gives rise to a plethora of exotic light -matter interactions. In particular, photonic lattices can seed long-lived atom-photon bound states inside photonic band gaps. Here, we report on the concept and implementation of a novel microwave architecture consisting of an array of compact superconducting resonators in which we have embedded two frequency -tunable artificial atoms. We study the atom-field interaction and access previously unexplored coupling regimes, in both the single-and double-excitation subspace. In addition, we demonstrate coherent interactions between two atom-photon bound states, in both resonant and dispers…

Radiation processing: a versatile methodology to tune the structure of polymeric materials

2013

A Stochastic Decision Process Model for Optimization of Railway and Tramway Track Maintenance by means of Image Processing Technique

2013

One of the key targets for an efficient transport network management is the search for proper maintenance policies to guarantee acceptable safety and quality standards in the travel and to optimize available resource allocation. Methodologically, the proposed model presented in this paper uses the stochastic dynamic programming and in particular Markov decision processes applied to the rail wear conditions for the railway and tramway network. By performing the integrated analysis of the classes of variables which characterize the rail quality (in terms of safety), the proposed mathematical approach allows to find the solutions to the decision-making process related to the probability of det…

Automated Railway Signs Detection. Preliminary Results

2019

Abstract Nowadays safety in railways is mostly achieved by automated system technologies such as ERTMS/ETCS. Nevertheless, on local railways (suburban and regional lines) several tasks still depend on the choices and actions of a human crew. With the aim to improve safety in such type of railways, this research proposes a system for the automatic detection and recognition of railway signs by means of the digital image processing technique. First field applications, carried out on the Italian railway network, show that the proposed system is very accurate (the percentage of correctly detected railway signs is about 97%), even at high train speeds.

Reactive Compatibilization of PBT/EVA Blends with an Ethylene-Acrylic Acid Copolymer and a Low Molar Mass Bis-Oxazoline

2004

Polyesters and polyolefins form highly incompatible blends with poor properties and gross morphology that hinder any practical applications. In this work, the possibility to compatibilize an incompatible blend of poly(butylene terephthalate) (PBT) with ethylene vinyl acetate (EVA) by adding a bis-oxazoline compound, 2,2'-(1,3-phenylene)-bis(2-oxazoline) (PBO), and an ethylene acrylic acid copolymer (EAA) as compatibilizer precursors has been studied. The results indicate that the binary uncompatibilized blends show poor mechanical properties and a bad morphology with scarce adhesion between the phases. The situation is only slightly improved when the EAA is added while the best performance …

On the modification of the nitrile groups of acrylonitrile/butadiene/styrene into oxazoline in the melt

2000

Oxazoline functionality is well known to be highly reactive toward a lot of other functional groups like carboxyls, hydroxyls, mercaptans, and amines. In this work we report the possibility to modify the nitrile groups of an acrylonitrile/butadiene/styrene (ABS) copolymer into oxazoline in the molten state in the presence of aminoethanol as modifier agent and zinc acetate as a catalyst. The reaction has been carried out in a batch mixer and in a corotating twin screw extruder. The conversion of the nitrile groups into oxazoline has been verified by infrared spectroscopy, NMR analysis microanalysis and confirmed by thermomechanical characterization. The results indicate that the kinetic of g…

An Automatic Ontology-Based Approach to Support Logical Representation of Observable and Measurable Data for Healthy Lifestyle Management: Proof-of-C…

2020

Background Lifestyle diseases, because of adverse health behavior, are the foremost cause of death worldwide. An eCoach system may encourage individuals to lead a healthy lifestyle with early health risk prediction, personalized recommendation generation, and goal evaluation. Such an eCoach system needs to collect and transform distributed heterogenous health and wellness data into meaningful information to train an artificially intelligent health risk prediction model. However, it may produce a data compatibility dilemma. Our proposed eHealth ontology can increase interoperability between different heterogeneous networks, provide situation awareness, help in data integration, and discover…

Fault diagnosis of induction motors broken rotor bars by pattern recognition based on noise cancelation

2014

Current signal monitoring (CSM) can be used as an effective tool for diagnosing broken rotor bars fault in induction motors. In this paper, fault diagnosis and classification based on artificial neural networks (ANNs) is done in two stages. In the first stage, a filter is designed to remove irrelevant fault components (such as noise) of current signals. The coefficients of the filter are obtained by least square (LS) algorithm. Then by extracting suitable time domain features from filter's output, a neural network is trained for fault classification. The output vector of this network is represented in one of four categories that includes healthy mode, a 5 mm crack on a bar, one broken bar, …