Search results for "UML"
showing 10 items of 407 documents
Web Usage Mining by Neural Hybrid Prediction with Markov Chain Components
2021
This paper presents and evaluates a two-level web usage prediction technique, consisting of a neural network in the first level and contextual component predictors in the second level. We used Markov chains of different orders as contextual predictors to anticipate the next web access based on specific web access history. The role of the neural network is to decide, based on previous behaviour, whose predictor’s output to use. The predicted web resources are then prefetched into the cache of the browser. In this way, we considerably increase the hit rate of the web browser, which shortens the load times. We have determined the optimal configuration of the proposed hybrid predictor on a real…
Ventricular fibrillation detection from ECG surface electrodes using different filtering techniques, window length and artificial neural networks
2017
Medical personnel face many difficulties when diagnosing ventricular fibrillation (VF). Its correct diagnosis allows to decide the right medical treatment and, therefore, it is essential to tell it apart adequately from ventricular tachycardia (VT) and other arrhythmias. If the required therapy is not appropriate, the personnel could cause serious injuries or even induce VF. In this work, a diagnosis automatic system for the detection of VF through feature extraction was developed. To verify the validity of this method, an Artificial Neural Network (ANN) classifier was used. The ECG signals used were obtained from the MIT-BIH Malignant Ventricular Arrhythmia Database and AHA (2000 series) d…
A Flexible 4G/5G Control Platform for Fingerprint-based Indoor Localization
2019
In this paper we propose a centralized SDN platform devised to control indoor femto-cells for supporting multiple network-wide optimizations and applications. In particular, we focus on an example localization application in order to enlighten the main functionalities and potentialities of the approach. First, we demonstrate that the platform can be exploited for reconfiguring some operational procedures, based on standard signalling mechanisms, at the programmable femto-cells; these procedures enable customized logics for collecting measurements reports from mobile terminals. Second, assuming that high-density devices such as smart objects are disseminated in the controlled indoor space, w…
Improving the Competency of Classifiers through Data Generation
2001
This paper describes a hybrid approach in which sub-symbolic neural networks and symbolic machine learning algorithms are grouped into an ensemble of classifiers. Initially each classifier determines which portion of the data it is most competent in. The competency information is used to generated new data that are used for further training and prediction. The application of this approach in a difficult to learn domain shows an increase in the predictive power, in terms of the accuracy and level of competency of both the ensemble and the component classifiers.
N-body simulations with generic non-Gaussian initial conditions I: Power Spectrum and halo mass function
2010
We address the issue of setting up generic non-Gaussian initial conditions for N-body simulations. We consider inflationary-motivated primordial non-Gaussianity where the perturbations in the Bardeen potential are given by a dominant Gaussian part plus a non-Gaussian part specified by its bispectrum. The approach we explore here is suitable for any bispectrum, i.e. it does not have to be of the so-called separable or factorizable form. The procedure of generating a non-Gaussian field with a given bispectrum (and a given power spectrum for the Gaussian component) is not univocal, and care must be taken so that higher-order corrections do not leave a too large signature on the power spectrum.…
Implementation of the chemistry module MECCA (v2.5) in the modal aerosol version of the Community Atmosphere Model component (v3.6.33) of the Communi…
2013
Abstract. A coupled atmospheric chemistry and climate system model was developed using the modal aerosol version of the National Center for Atmospheric Research Community Atmosphere Model (modal-CAM; v3.6.33) and the Max Planck Institute for Chemistry's Module Efficiently Calculating the Chemistry of the Atmosphere (MECCA; v2.5) to provide enhanced resolution of multiphase processes, particularly those involving inorganic halogens, and associated impacts on atmospheric composition and climate. Three Rosenbrock solvers (Ros-2, Ros-3, RODAS-3) were tested in conjunction with the basic load-balancing options available to modal-CAM (1) to establish an optimal configuration of the implicitly-sol…
Implementation of the Community Earth System Model (CESM) version 1.2.1 as a new base model into version 2.50 of the MESSy framework
2016
Abstract. The Community Earth System Model (CESM1), maintained by the United States National Centre for Atmospheric Research (NCAR) is connected with the Modular Earth Submodel System (MESSy). For the MESSy user community, this offers many new possibilities. The option to use the Community Atmosphere Model (CAM) atmospheric dynamical cores, especially the state-of-the-art spectral element (SE) core, as an alternative to the ECHAM5 spectral transform dynamical core will provide scientific and computational advances for atmospheric chemistry and climate modelling with MESSy. The well-established finite volume core from CESM1(CAM) is also made available. This offers the possibility to compare …
Service discovery protocols in D2D-enabled cellular networks: Reactive versus proactive
2014
Device-to-Device (D2D) communication, which allows access services offered by nearby devices bypassing the base station, has been regarded as an essential component of the emerging 5G mobile networks. Many advantages can be provided by this direct communication paradigm such as high data rate, traffic offloading, range extension, as well as proximity services and social networking. In such a context, service discovery approaches need to be investigated. In this paper, we propose two protocols for service discovery, namely, reactive (pull) discovery and proactive (push) discovery in infrastructure-coordinated D2D networks. The protocol overhead is calculated and numerical results are provide…
Numerical and experimental validation of a LiFePO<inf>4</inf> battery model at steady state and transient operations
2013
In the paper some of the battery models proposed in literature are analysed in order to predict the battery performance and, then, make sure that the Battery Management System (BMS) that is a key component to check and control the status of the batteries within their specified safe operating conditions, works in best conditions. In fact to reach an extended battery lifetime and increase the reliability of the system, is necessary to guarantee an accurate evaluation of the state of the whole stack of batteries to track their operations. Therefore, an accurate battery model that captures the dynamics of the battery is required. Lithium batteries are in particular considered because of their h…
Tunable antenna system for plug&amp;play satellite avionics: Prototyping and test
2014
In the framework of an ESA program, a new architecture for plug&play compact antenna systems in the X band has been investigated and experimentally verified by many prototypes. The proposed antenna system takes inspiration from the LEGO building toys: the basic component of the new architecture is a 2.7cm-cube complex module that integrates a three-dimensional local network and a programmable mechanism based on the bonding-wire technology to select one among three polarization options. Elemental blocks can be augmented by accessories to shape the beam and may be used in array configuration over boards provided with cluster-level beamforming networks. Measurements have been performed for bot…