Search results for "Mach"
showing 10 items of 3360 documents
Vers une assistance informatisée au diagnostic de la qualité ergonomique d'interfaces
2000
International audience; Notre objectif ici est d'encourager les concepteurs à s'intéresser aux usages de leur produit en prenant davantage en compte les facteurs humains dans la phase de test qui est souvent focalisée sur les aspects techniques. L'idée dans cette étude est donc de faciliter le recours aux utilisateurs comme source d'évaluation lors des tests de conception en apportant aux concepteurs un environnement logiciel de test pratique à mettre en œuvre pour faire évaluer leurs propres produits par des utilisateurs. Nous avons mené deux expériences de nature à explorer la faisabilité de ce projet.
Large-scale nonlinear dimensionality reduction for network intrusion detection
2017
International audience; Network intrusion detection (NID) is a complex classification problem. In this paper, we combine classification with recent and scalable nonlinear dimensionality reduction (NLDR) methods. Classification and DR are not necessarily adversarial, provided adequate cluster magnification occurring in NLDR methods like $t$-SNE: DR mitigates the curse of dimensionality, while cluster magnification can maintain class separability. We demonstrate experimentally the effectiveness of the approach by analyzing and comparing results on the big KDD99 dataset, using both NLDR quality assessment and classification rate for SVMs and random forests. Since data involves features of mixe…
Towards a Great Design of Conceptual Modelling
2020
Humankind faces a most crucial mission; we must endeavour, on a global scale, to restore and improve our natural and social environments. This is a big challenge for global information systems development and for their modelling. In this paper, we discuss on different aspects of conceptual modelling in global environmental context. The paper is the summary of the panel session “The Future of Conceptual Modelling” in the 29th International Conference on Information Modelling and Knowledge Bases. peerReviewed
The Development and Precision of a Custom-Made Skitester
2021
In the sport of cross-country skiing, equipment has a direct influence on results. Ski teams do extensive testing of different ski base grinds and products on a yearly basis. To achieve reliable results, the quality of methods used for testing skis needs to be taken in to account in addition to factors including the physical characteristics of testing personnel and changes in weather conditions. The aim of this study was to introduce a custom-made skitester, that was developed for testing skis on real snow, in laboratory conditions, and to evaluate its precision. The current skitester is capable of glide testing both classic and skate skis as well as kick simulation for the testing of grip …
Unstable feature relevance in classification tasks
2011
Aberrant brain functional networks in type 2 diabetes mellitus: A graph theoretical and support-vector machine approach
2022
ObjectiveType 2 diabetes mellitus (T2DM) is a high risk of cognitive decline and dementia, but the underlying mechanisms are not yet clearly understood. This study aimed to explore the functional connectivity (FC) and topological properties among whole brain networks and correlations with impaired cognition and distinguish T2DM from healthy controls (HC) to identify potential biomarkers for cognition abnormalities.MethodsA total of 80 T2DM and 55 well-matched HC were recruited in this study. Subjects’ clinical data, neuropsychological tests and resting-state functional magnetic resonance imaging data were acquired. Whole-brain network FC were mapped, the topological characteristics were ana…
On Assessing Vulnerabilities of the 5G Networks to Adversarial Examples
2022
The use of artificial intelligence and machine learning is recognized as the key enabler for 5G mobile networks which would allow service providers to tackle the network complexity and ensure security, reliability and allocation of the necessary resources to their customers in a dynamic, robust and trustworthy way. Dependability of the future generation networks on accurate and timely performance of its artificial intelligence components means that disturbance in the functionality of these components may have negative impact on the entire network. As a result, there is an increasing concern about the vulnerability of intelligent machine learning driven frameworks to adversarial effects. In …
Kernels and Graphs on M25 + H
2023
Codes related to article "Graphs and Kernelized Learning Applied to Interactions of Hydrogen with Doped Gold Nanoparticle Electrocatalysts". There are two main types of codes: codes to transform a catalytic system of protected gold nanoparticle and a single hydrogen atom into a graph-based representation, and codes to run kernel-based machine learning methods to predict interaction energies between the nanoparticle and the hydrogen atom. This is a snapshot of the code dataset that has been taken on 06.06.2023. A more detailed description of the data and the address to the GitLab repository for the latest version of the code can be found from the parent dataset of this data publication.
Kernels and Graphs on M25 + H (parent repository)
2023
The repository contains codes related to article "Graphs and Kernelized Learning Applied to Interactions of Hydrogen with Doped Gold Nanoparticle Electrocatalysts". There are two main types of codes: codes to transform a catalytic system of protected gold nanoparticle and a single hydrogen atom into a graph-based representation, and codes to run kernel-based machine learning methods to predict interaction energies between the nanoparticle and the hydrogen atom. This is the metadata for the parent repository of the codes. Updates and possible corrections are documented in the GitLab project, where the material saved and shared. The GitLab project can be found and downloaded from the followin…
Supplementary data for the article "Machine Learning for Predicting Chemical Potentials of Multifunctional Organic Compounds in Atmospherically Relev…
2022
The data set contains the supplementary data of the article "Machine Learning for Predicting Chemical Potentials of Multifunctional Organic Compounds in Atmospherically Relevant Solutions" published in J. Phys. Chem. Lett., https://doi.org/10.1021/acs.jpclett.2c02612. The data includes: - A machine learning (EMLM) model for predicting chemical potentials of individual conformers of multifunctional organic compounds calculated by the COSMOtherm program - COSMO-files used for training and testing the EMLM model - Descriptors and chemical potentials used for the training and testing the model Artikkelin "Machine Learning for Predicting Chemical Potentials of Multifunctional Organic Compounds i…