检索结果-内蒙古大学图书馆

Role of partial functionals in the study of variational systems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Stan, Andrei Faculty of Mathematics and Computer Science Babes -Bolyai University Cluj-Napoca400084 Romania Tiberiu Popoviciu Institute of Numerical Analysis Romanian Academy Cluj-Napoca400110 Romania

Applying techniques originally developed for systems lacking a variational structure, we establish conditions for the existence of solutions in systems that possess this property but their energy functional is unbounded both lower and below. We show that, in general, our conditions differ from those in the classical mountain pass approach by Ambroseti-Rabinovitz when dealing with systems of this type. Our theory is put into practice in the context of a coupled system of Stokes equations with reaction terms, where we establish sufficient conditions for the existence of a solution. The systems under study are intermediary between gradient-type systems and Hamiltonian systems. © 2023, CC BY.

关键词： Variational techniques

Survival of Listeria Monocytogenes Biofilms and Planktonic Cells on Cooked Ham in a Contamination-Storage-Digestion Process

学校读者我要写书评

暂无评论

SSRN

SSRN 2025年

作者： Serrano-Heredia, Salud María Sánchez-Martín, Javier López Carmona, José Luis Sánchez-Gutiérrez, Mónica Valero Díaz, Antonio Jiménez, Elena Carrasco CeiA3 Universidad de Córdoba Campus Rabanales Córdoba14014 Spain KDISLab Department of Computer Science and Numerical Analysis University of Córdoba Spain Rabanales Campus Córdoba14071 Spain

In 2023, listeriosis experienced a significant increase in Europe, with 2,952 invasive cases and 19.70% mortality rate, being the ready-to-eat foods category identified as the mostly involved. This study focused on the survival of L. monocytogenes through a process of food contamination-storage-digestion. For this, it was assayed the transfer of biofilm and inoculation of planktonic cells to cooked ham, and the subsequent survival of the pathogen (planktonic or biofilm) after in vitro digestion with or without storage of cooked ham vacuum-packed and stored at 7°C for 7 days. Transfer results to cooked ham after 90 seconds of contact revealed inter-strain variability, with a global transfer rate of 14.07%. From biofilm, initial concentration of L. monocytogenes in the food, 3.53 log CFU/cm2 on average, grew ≈ 0.5 log after storage. Digestion, both immediate after contamination or after food storage, resulted in a reduction of ≈ 0.5 log. However, in the case of planktonic cells, although reduction after immediate digestion (≈ -2.1 log) and after storage (≈ - 0.6 log) were observed as expected (given their less resistance than biofilm cells), an unexpectedly high concentration of the pathogen was found after food storage and digestion (even with a slight increase of ≈ 0.25 log). It is plausible that a biofilm was formed during storage of the contaminated food with planktonic cells. In all cases, high variability in numbers was observed after storage and digestion, being L196 the most resistant strain. More research in omics sciences is needed to clarify L. monocytogenes behaviour. © 2025, The Authors. All rights reserved.

关键词： Food storage

An optimal control study for a two-strain SEIR epidemic model with saturated incidence rates and treatment

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Allali, Karam Balde, Mouhamadou A.M.T. Ndiaye, Babacar M. Laboratory of Mathematics Computer Science and Applications Faculty of Sciences and Technologies University Hassan II of Casablanca PO BOX 146 Mohammedia Morocco Laboratory of Mathematics of Decision and Numerical Analysis University of Cheikh Anta Diop Dakar Senegal

This work will study an optimal control problem describing the two-strain SEIR epidemic model. The studied model is in the form of six nonlinear differential equations illustrating the dynamics of the susceptibles and the exposed, the infected, and the recovered individuals. The exposed and the infected compartments are each divided into two sub-classes representing the first and the second strain. The model includes two saturated rates and two treatments for each strain. We begin our study by showing the well-posedness of our problem. The basic reproduction number is calculated and depends mainly on the reproduction numbers of the first and second strains. The global stability of the disease-free equilibrium is fulfilled. The optimal control study is achieved by using the Pontryagin minimum principle. numerical simulations have shown the importance of therapy in minimizing the infection's effect. By administrating suitable therapies, the disease's severity decreases considerably. The estimation of parameters as well as a comparison study with COVID-19 clinical data are fulfilled. It was shown that the mathematical model results fits well the clinical data. © 2024, CC BY-NC-ND.

关键词： Nonlinear equations

dlordinal: a Python package for deep ordinal classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bérchez-Moreno, Francisco Vargas, Víctor M. Ayllón-Gavilán, Rafael Guijo-Rubio, David Hervás-Martínez, César Fernández, Juan C. Gutiérrez, Pedro A. Department of Computer Science and Numerical Analysis University of Córdoba Córdoba Spain Department of Clinical-Epidemiological Research in Primary Care Instituto Maimónides de Investigación Biomédica de Córdoba Spain

dlordinal is a new Python library that unifies many recent deep ordinal classification methodologies available in the literature. Developed using PyTorch as underlying framework, it implements the top performing state-of-the-art deep learning techniques for ordinal classification problems. Ordinal approaches are designed to leverage the ordering information present in the target variable. Specifically, it includes loss functions, various output layers, dropout techniques, soft labelling methodologies, and other classification strategies, all of which are appropriately designed to incorporate the ordinal information. Furthermore, as the performance metrics to assess novel proposals in ordinal classification depend on the distance between target and predicted classes in the ordinal scale, suitable ordinal evaluation metrics are also included. dlordinal is distributed under the BSD-3-Clause license and is available at https://***/ayrna/dlordinal. © 2024, CC BY-NC-SA.

关键词： Python

Automated Machine Learning for Test Case Prioritization

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Romero, José Raúl Ramírez, Aurora García-Martínez, Carlos Dept. of Computer Science and Numerical Analysis University of Córdoba AN Córdoba14071 Spain Andalusian Research Institute in Data Science and Computational Intelligence University of Córdoba AN Córdoba14071 Spain

Test case prioritization (TCP) involves ordering and selecting the most relevant test cases to verify that the current functionality of a software system remains unaffected by code changes. Recently, TCP has been solved by machine learning (ML), predicting the failure probability of each test case. However, software engineers may struggle to identify and implement the most suitable predictive models for TCP. As new builds adapt the test suite being tested, the model performance may decline as these new builds are incorporated. In this study, we address these challenges by applying automated workflow composition and hyperparameter optimization. Both are considered tasks within automatic machine learning (AutoML). With this aim, our proposal employs grammar-guide genetic programming as the underlying mechanism for implementing the AutoML algorithm. Our experimental results demonstrate that our approach can adapt to the particularities of the system under test, selecting the most appropriate workflow and hyperparameters for each build. More importantly, our approach eliminates the need for testers to possess extensive knowledge of ML, while allowing them to inspect workflows to understand the evolution of the prioritization process. This research showcases the potential of AutoML in software engineering, specifically for the TCP problem. © 2023, The Authors. All rights reserved.

关键词： Genetic programming

Vision-based Situational Graphs Exploiting Fiducial Markers for the Integration of Semantic Entities

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tourani, Ali Bavle, Hriday Sanchez-Lopez, Jose Luis Avşar, Deniz Işınsu Salinas, Rafael Muñoz Voos, Holger University of Luxembourg Luxembourg Institute for Advanced Studies University of Luxembourg Luxembourg Department of Physics & Materials Science University of Luxembourg Luxembourg Department of Computer Science and Numerical Analysis University of Córdoba Rabanales Campus Spain

Situational Graphs (S-Graphs) merge geometric models of the environment generated by Simultaneous Localization and Mapping (SLAM) approaches with 3D scene graphs into a multi-layered jointly optimizable factor graph. As an advantage, S-Graphs not only offer a more comprehensive robotic situational awareness by combining geometric maps with diverse hierarchically organized semantic entities and their topological relationships within one graph, but they also lead to improved performance of localization and mapping on the SLAM level by exploiting semantic information. In this paper, we introduce a vision-based version of S-Graphs where a conventional Visual SLAM (VSLAM) system is used for low-level feature tracking and mapping. In addition, the framework exploits the potential of fiducial markers (both visible as well as our recently introduced transparent or fully invisible markers) to encode comprehensive information about environments and the objects within them. The markers aid in identifying and mapping structural-level semantic entities, including walls and doors in the environment, with reliable poses in the global reference, subsequently establishing meaningful associations with higher-level entities, including corridors and rooms. However, in addition to including semantic entities, the semantic and geometric constraints imposed by the fiducial markers are also utilized to improve the reconstructed map’s quality and reduce localization errors. Experimental results on a real-world dataset collected using legged robots show that our framework excels in crafting a richer, multi-layered hierarchical map and enhances robot pose accuracy at the same time. © 2023, CC BY.

关键词： Mapping

A memetic dynamic coral reef optimisation algorithm for simultaneous training, design, and optimisation of artificial neural networks (vol 14, 6961, 2024)

学校读者我要写书评

暂无评论

SCIENTIFIC REPORTS 2024年第1期14卷 1-22页

作者： Berchez-Moreno, Francisco Duran-Rosal, Antonio M. Martinez, Cesar Hervas Gutierrez, Pedro A. Fernandez, Juan C. Department of Computer Science and Numerical Analysis University of Córdoba Córdoba Spain Maimonides Biomedical Research Institute of Córdoba IMIBIC University of Córdoba 14071 Córdoba Spain Department of Quantitative Methods Universidad Loyola Andalucía Córdoba Spain

Artificial Neural Networks (ANNs) have been used in a multitude of real-world applications given their predictive capabilities, and algorithms based on gradient descent, such as Backpropagation (BP) and variants, are usually considered for their optimisation. However, these algorithms have been shown to get stuck at local optima, and they require a cautious design of the architecture of the model. This paper proposes a novel memetic training method for simultaneously learning the ANNs structure and weights based on the Coral Reef Optimisation algorithms (CROs), a global-search metaheuristic based on corals’ biology and coral reef formation. Three versions based on the original CRO combined with a Local Search procedure are developed: (1) the basic one, called Memetic CRO; (2) a statistically guided version called Memetic SCRO (M-SCRO) that adjusts the algorithm parameters based on the population fitness; (3) and, finally, an improved Dynamic Statistically-driven version called Memetic Dynamic SCRO (M-DSCRO). M-DSCRO is designed with the idea of improving the M-SCRO version in the evolutionary process, evaluating whether the fitness distribution of the population of ANNs is normal to automatically decide the statistic to be used for assigning the algorithm parameters. Furthermore, all algorithms are adapted to the design of ANNs by means of the most suitable operators. The performance of the different algorithms is evaluated with 40 classification datasets, showing that the proposed M-DSCRO algorithm outperforms the other two versions on most of the datasets. In the final analysis, M-DSCRO is compared against four state-of-the-art methods, demonstrating its superior efficacy in terms of overall accuracy and minority class performance.

关键词： Artificial neural networks Classification Coral reef optimisation algorithm Local search Neuroevolution Robust estimators

Integrating Physics and Data-Driven Approaches: An Explainable and Uncertainty-Aware Hybrid Model for Wind Turbine Power Prediction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Gijón, Alfonso Eiraudo, Simone Manjavacas, Antonio Schiera, Daniele Salvatore Molina-Solana, Miguel Gómez-Romero, Juan Department of Computer Science and Artificial Intelligence Universidad de Granada Granada18071 Spain Energy Center Lab Politecnico di Torino Torino10138 Italy Deparment of Informatics and Numerical Analysis Universidad de Córdoba Córdoba14014 Spain

The rapid growth of the wind energy sector underscores the urgent need to optimize turbine operations and ensure effective maintenance through early fault detection systems. While traditional empirical and physics-based models offer approximate predictions of power generation based on wind speed, they often fail to capture the complex, non-linear relationships between other input variables and the resulting power output. Data-driven machine learning methods present a promising avenue for improving wind turbine modeling by leveraging large datasets, enhancing prediction accuracy but often at the cost of interpretability. In this study, we propose a hybrid semi-parametric model that combines the strengths of both approaches, applied to a dataset from a wind farm with four turbines. The model integrates a physics-inspired submodel, providing a reasonable approximation of power generation, with a non-parametric submodel that predicts the residuals. This non-parametric submodel is trained on a broader range of variables to account for phenomena not captured by the physics-based component. The hybrid model achieves a 37% improvement in prediction accuracy over the physics-based model. To enhance interpretability, SHAP values are used to analyze the influence of input features on the residual submodel’s output. Additionally, prediction uncertainties are quantified using a conformalized quantile regression method. The combination of these techniques, alongside the physics grounding of the parametric submodel, provides a flexible, accurate, and reliable framework. Ultimately, this study opens the door for evaluating the impact of unmodeled variables on wind turbine power generation, offering a basis for potential optimization. © 2025, CC BY.

关键词： Windmill

Evolving machine learning workflows through interactive AutoML

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Barbudo, Rafael Ramírez, Aurora Romero, José Raúl Department of Computer Science and Numerical Analysis University of Córdoba Córdoba14071 Spain Departamento de Lenguajes y Ciencias de la Computación University of Málaga Málaga29071 Spain Córdoba Spain

Automatic workflow composition (AWC) is a relevant problem in automated machine learning (AutoML) that allows finding suitable sequences of preprocessing and prediction models together with their optimal hyperparameters. This problem can be solved using evolutionary algorithms and, in particular, grammar-guided genetic programming (G3P). Current G3P approaches to AWC define a fixed grammar that formally specifies how workflow elements can be combined and which algorithms can be included. In this paper we present iEvoFlow, an interactive G3P algorithm that allows users to dynamically modify the grammar to prune the search space and focus on their regions of interest. Our proposal is the first to combine the advantages of a G3P method with ideas from interactive optimisation and human-guided machine learning, an area little explored in the context of AutoML. To evaluate our approach, we present an experimental study in which 20 participants interact with iEvoFlow to evolve workflows according to their preferences. Our results confirm that the collaboration between iEvoFlow and humans allows us to find high-performance workflows in terms of accuracy that require less tuning time than those found without human *** Codes 68T05 © 2024, CC BY.

关键词： Machine learning