检索结果-内蒙古大学图书馆

Hybrid system of optimal self organizing maps and hidden markov model for Arabic digits recognition

学校读者我要写书评

暂无评论

WSEAS Transactions on Systems 2014年 13卷 606-616页

作者： En-Naimani, Zakariae Lazaar, Mohamed Ettaouil, Mohamed Modelling and Scientific Computing Laboratory Faculty of Science and Technology University Sidi Mohammed Ben Abdellah Fez Morocco Abdelmalek Essaadi University Tetouan Morocco

Thanks to Automatic Speech Recognition (ASR), a lot of machines can nowadays emulate human being ability to understand and speak natural language. However, ASR problematic could be as interesting as it is difficult. Its difficulty is precisely due to the complexity of speech processing, which takes into consideration many aspects: acoustic, phonetic, syntactic, etc. Thus, the most commonly used technology, in the context of speech recognition, is based on statistical models. Especially, the Hidden Markov Models which are capable of simultaneously modeling frequency and temporal characteristics of the speech signal. There is also the alternative of using Neuronal Networks. But another interesting framework applied in ASR is indeed the hybrid Artificial Neural Network (ANN) and Hidden Markov Model (HMM) speech recognizer that improves the accuracy of the two models. In the present work, we propose an Arabic digits recognition system based on hybrid Optimal Artificial Neural Network and Hidden Markov Model (OANN/HMM). The main innovation in this work is the use of an optimal neural network to determine the optimal groups, unlike in classical Kohonen approach. The numerical results are powerful and show the practical interest of our approach.

关键词： Hidden Markov models

Building Cross-Scale Models of Epigenetic Mechanisms

学校读者我要写书评

暂无评论

Building Cross-Scale Models of Epigenetic Mechanisms

IEEE International Conference on Bioinformatics and Biomedicine

作者： Heather J. Ruskin Dimitri Perrin Irina A. Roznovat Centre for Scientific Computing & Complex Systems Modelling (SCI-SYM) School of Computing Dublin City University Laboratory for Systems Biology RIKEN Center for Developmental Biology

ISBN: (纸本)9781479956708

Epigenetic changes correspond to heritable modifications of the chromosome structure, which do not involve alteration of the DNA sequence but do affect gene expression. These mechanisms play an important role in normal cell differentiation, but aberration is associated also with several diseases, including cancer and neural disorders. In consequence, despite intensive studies in recent years, the contribution of modifications remains largely unquantified due to overall system complexity and insufficient data. Computational models can provide powerful auxiliary tools to experimentation, not least as scales from the sub-cellular through cell populations (or to networks of genes) can be spanned. In this paper, the challenges to development, of realistic cross-scale models, are discussed and illustrated with respect to current work.

关键词： Cross-scale/multi-scale Computational modelling DNA methylation Epigenetics Cancer Colon crypt component

Local Embedded Discrete Fracture Model (LEDFM)

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Losapio, Davide Scotti, Anna MOX Laboratory for Modelling and Scientific Computing Department of Mathematics Politecnico di Milano Via Edoardo Bonardi 9 MI Milan20133 Italy

The study of flow in fractured porous media is a key ingredient for many geoscience applications, such as reservoir management and geothermal energy production. modelling and simulation of these highly heterogeneous and geometrically complex systems require the adoption of non-standard numerical schemes. The Embedded Discrete Fracture Model (EDFM) is a simple and effective way to account for fractures with coarse and regular grids, but it suffers from some limitations: it assumes a linear pressure distribution around fractures, which holds true only far from the tips and fracture intersections, and it can be employed for highly permeable fractures only. In this paper we propose an improvement of EDFM which aims at overcoming these limitations computing an improved coupling between fractures and the surrounding porous medium by a) relaxing the linear pressure distribution assumption, b) accounting for impermeable fractures modifying near-fracture transmissibilities. These results are achieved by solving different types of local problems with a fine conforming grid, and computing new transmissibilities (for connections between fractures and the surrounding porous medium and those through the porous medium itself near to the fractures). Such local problems are inspired from numerical upscaling techniques present in the literature. The new method is called Local Embedded Discrete Fracture Model (LEDFM) and the results obtained from several numerical tests confirm the aforementioned improvements. Copyright © 2022, The Authors. All rights reserved.

关键词： Fracture

Retrieval of aerosol properties from in situ, multi-angle light scattering measurements using invertible neural networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Boiger, Romana Modini, Rob L. Moallemi, Alireza Degen, David Gysel-Beer, Martin Adelmann, Andreas Paul Scherrer Institut Laboratory for Scientific Computing and Modelling Forschungsstrasse 111 Villigen5232 Switzerland Paul Scherrer Institut Laboratory of Atmospheric Chemistry Forschungsstrasse 111 Villigen5232 Switzerland

Atmospheric aerosols have a major influence on the earth's climate and public health. Hence, studying their properties and recovering them from light scattering measurements is of great importance. State of the art retrieval methods such as pre-computed look-up tables and iterative, physics-based algorithms can suffer from either accuracy or speed limitations. These limitations are becoming increasingly restrictive as instrumentation technology advances and measurement complexity increases. Machine learning algorithms offer new opportunities to overcome these problems, by being quick and precise. In this work we present a method, using invertible neural networks to retrieve aerosol properties from in situ light scattering measurements. In addition, the algorithm is capable of simulating the forward direction, from aerosol properties to measurement data. The applicability and performance of the algorithm are demonstrated with simulated measurement data, mimicking in situ laboratory and field measurements. With a retrieval time in the millisecond range and a weighted mean absolute percentage error of less than 1.5%, the algorithm turned out to be fast and accurate. By introducing Gaussian noise to the data, we further demonstrate that the method is robust with respect to measurement errors. In addition, realistic case studies are performed to demonstrate that the algorithm performs well even with missing measurement data. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

V-cycle multigrid algorithms for discontinuous Galerkin methods on non-nested polytopic meshes

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Antonietti, P.F. Pennesi, G. MOX-Laboratory for Modelling and Scientific Computing Dipartimento di Matematica Po-litecnico di Milano Piazza Leonardo da Vinci 32 Milano20133 Italy

65F10 · 65M55 · 65N22In this paper we analyse the convergence properties of V-cycle multigrid algorithms for the numerical solution of the linear system of equations arising from discontinuous Galerkin discretization of second-order elliptic partial differential equations on polytopal meshes. Here, the sequence of spaces that stands at the basis of the multigrid scheme is possibly non nested and is obtained based on employing agglomeration with possible edge/face coarsening. We prove that the method converges uniformly with respect to the granularity of the grid and the polynomial approximation degree p, provided that the number of smoothing steps, which depends on p, is chosen sufficiently large.65F10, 65M55, 65N22 Copyright © 2017, The Authors. All rights reserved.

关键词： Galerkin methods

Fast Uncertainty Quantification of Spent Nuclear Fuel with Neural Networks

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Albà, Arnau Adelmann, Andreas Münster, Lucas Rochman, Dimitri Boiger, Romana Paul Scherrer Institut PSI Forschungstrasse 111 Villigen5232 Switzerland ETH Zürich Rämistrasse 101 Zurich8092 Switzerland Laboratory for Scientific Computing and Modelling Switzerland

The accurate assessment of spent nuclear fuel (SNF) characteristics is essential for nuclear energy safety, efficiency, sustainability, safeguards and waste management. Traditional physics-based models, while reliable, are computationally intensive. This paper presents a neural network (NN) surrogate model for efficient SNF characterisation. We trained the NN using CASMO5 lattice calculations, predicting accurately decay heat and nuclide concentrations, from inputs like enrichment, burnup, cooling time, boron concentration and fuel temperature. The NN model was validated against physics-based decay heat simulations and measurements. The NN also greatly reduced the costs of sensitivity analysis and uncertainty quantification. The results are comparable to CASMO5, with reduced computational costs (including generating training samples) by a factor of 10 or more. Our findings demonstrate the feasibility of NNs as surrogate models for fast characterization of SNF, improving computational efficiency in assessing nuclear fuel behavior and associated risks. © 2023, The Authors. All rights reserved.

关键词： Sensitivity analysis

CFD Simulations of the Step Height Effects on Heat Transfer for a Turbulent Wall Jet Flow in an Unconfined Backward Facing Step Configuration 20

学校读者我要写书评

暂无评论

CFD Simulations of the Step Height Effects on Heat Transfer ...

20th International Topical Meeting on Nuclear Reactor Thermal Hydraulics, NURETH 2023

作者： Ouldrebai, H. Halouane, Y. Dehbi, A. Laboratoire de Mécanique des Fluides Théorique et Apppliquée Physics Institute University of Sciences and Technology Houari Boumediene BP32 Bab Ezzouar Algiers Algeria Laboratoire Energétique Mécanique et Ingénieries Université de Boumerdes Boumerdes35000 Algeria Laboratory for Scientific Computing and Modelling Paul Scherrer Institut Villigen5232 Switzerland

ISBN: (纸本)9780894487934

A CFD study has been performed to analyze a wall jet flow intended to cool a hot horizontal plate in an unconfined backward facing step (BFS) configuration. This work combines dynamic and thermal fields analyses and focuses on the effect of the entrance diameter-to-step-height ratio D/H on local heat transfer. Specific locations along the heated plate have been examined in detail to better understand the effect of the BFS configuration on the wall jet flow structure. Parameters of interest which have been analyzed include the position of maximum heat transfer xmax, the position of maximum wall temperature xTmax and the recirculation zone size described by the reattachment position xr. Several Reynolds number values has been studied, in both isothermal laminar flow (50 © 2023 Proceedings of the 20th International Topical Meeting on Nuclear Reactor Thermal Hydraulics, NURETH 2023. All rights reserved.

关键词： Reynolds number

Vehicle routing problem on a road-network with fuzzy time windows for perishable food 5

学校读者我要写书评

暂无评论

Vehicle routing problem on a road-network with fuzzy time wi...

5th IEEE International Smart Cities Conference, ISC2 2019

作者： Raoui, Hanane El Oudani, Mustapha Pelta, David Alaoui, Ahmed El Hilali Aroudi, Abdelali El Université Internationale de Rabat ESIN TIC Lab Rabat Morocco Universidad de Granada Depto. de Ciencias de la Computación e I.A. Granada Spain Modelling and Scientific Computing Laboratory Sidi Mohamed Ben Abdellah University Fez Morocco Euro-Mediterranean University of Fez Fez Morocco Universitat Rovira i Virgili Tarragona Spain

ISBN: (纸本)9781728108469

In this paper, a Capacitated Vehicle Routing Problem with Fuzzy Time Windows and multiple Paths (CVRPFTW-P) for the distribution of perishable food in urban area is proposed and solved. We adopt the real road network modeling approach considering alternative paths to find efficient routes based on real spatial data. The parametric approach is used to decompose the original fuzzy problem into a set of crisp models (CVRPFTW-P). Experiments based on a designed case study in Casablanca city of Morocco was conducted to evaluate the impact of flexible time windows on distribution costs and results show that CVRPFTW-P model can attain significant cost-saving while ensuring a good level of service. © 2019 IEEE.

关键词： Roads and streets

Randomized double and triple Kaczmarz for solving extended normal equations

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Du, Kui Sun, Xiao-Hui School of Mathematical Sciences Fujian Provincial Key Laboratory of Mathematical Modelling and High Performance Scientific Computing Xiamen University Xiamen361005 China School of Mathematical Sciences Xiamen University Xiamen361005 China

The randomized Kaczmarz algorithm has received considerable attention recently because of its simplicity, speed, and the ability to approximately solve large-scale linear systems of equations. In this paper we propose randomized double and triple Kaczmarz algorithms to solve extended normal equations of the form A>Ax = A>b − c. The proposed algorithms avoid forming A>A explicitly and work for arbitrary A ∈ Rm×n (full rank or rank deficient, m ≥ n or m Copyright © 2020, The Authors. All rights reserved.

关键词： Linear systems