Výsledky vyhledávání - "Malkova, Aleksandra"

Akademický článek

Neural architecture search for radio map reconstruction with partially labeled data.

Autor: Malkova, Aleksandra¹ (AUTHOR), Amini, Massih-Reza¹ (AUTHOR) Massih-Reza.Amini@univ-grenoble-alpes.fr, Denis, Benoît² (AUTHOR), Villien, Christophe² (AUTHOR)

Publikováno v: Integrated Computer-Aided Engineering. 2024, Vol. 31 Issue 3, p285-305. 21p.

Zobrazit plný text záznamu

Plný text ve formátu HTML

Report

Self-Learning for Received Signal Strength Map Reconstruction with Neural Architecture Search

Autor: Malkova, Aleksandra, Pauletto, Loic, Villien, Christophe, Denis, Benoit, Amini, Massih-Reza

In this paper, we present a Neural Network (NN) model based on Neural Architecture Search (NAS) and self-learning for received signal strength (RSS) map reconstruction out of sparse single-snapshot input measurements, in the case where data-augmentat

Externí odkaz: http://arxiv.org/abs/2105.07768

Zobrazit plný text záznamu

Radio Map Reconstruction with Deep Neural Networks in a Weakly Labeled Learning Context with use of Heterogeneous Side Information

Autor: Malkova, Aleksandra, Amini, Massih-Reza, Denis, Benoît, Villien, Christophe

Publikováno v: 4th International Conference on Advances in Signal Processing and Artificial Intelligence
4th International Conference on Advances in Signal Processing and Artificial Intelligence, Oct 2022, Corfu, Greece
ASPAI 2022-4th International Conference on Advances in Signal Processing and Artificial Intelligence
ASPAI 2022-4th International Conference on Advances in Signal Processing and Artificial Intelligence, International Frequency Sensor Association (IFSA), Oct 2022, Corfu, Greece

International audience; Wireless localization is an essential component in Internet of Things applications. In this paper, we address the generalization problem of RSS map reconstruction for each city (usually, over gateways), relying on location-dep

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::546118869fc884e0e1a476d375b96d0f
https://hal.science/hal-03821815/file/ASPAI.pdf

Zobrazit plný text záznamu

Reconstruction de Cartes de Puissance Radio avec des réseaux de neurones profonds dans un contexte d'apprentissage faiblement étiqueté

Autor: Malkova, Aleksandra

Publikováno v: Artificial Intelligence [cs.AI]. Universite Grenoble Alpes, 2022. English. ⟨NNT : ⟩

The positioning of connected objects has become a major enabling feature for a variety of applications and services in the Internet of Things (IoT) domain. To avoid prohibitive power consumption and hardware complexity at the IoT nodes to be localize

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3515::51940e8d65d2dd3c5b02e90561afbe1a
https://theses.hal.science/tel-03740720

Zobrazit plný text záznamu

Techniques d'Auto-Apprentissage et Recherche Automatique d'Architecture Neuronale pour la Reconstruction de Cartes de Puissance Radio

Autor: Malkova, Aleksandra, Pauletto, Loïc, Villien, Christophe, Denis, Benoît, Amini, Massih-Reza

Publikováno v: Conférence sur l'apprentissage Automatique (CAp)
Conférence sur l'apprentissage Automatique (CAp), Jun 2021, Saint-Etienne (en ligne), France

International audience; Dans cet article, nous présentons un modèle de réseau de neurones (Neural Network, RN) s'appuyant sur une recherche d'architecture neuronale (Neural Architecture Search, NAS) et d'auto-apprentissage, que nous appliquonsà l

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::d1fe8825aec5253861c9f1a4fbf8e67b
https://hal.science/hal-03266118

Zobrazit plný text záznamu

DATASAFE: understanding Data Accidents for TrAffic SAFEty Acknowledgments

Autor: Malkova, Aleksandra, Arbel, Julyan, Delle Monache, Maria Laura

Publikováno v: Bayesian learning theory for complex data modelling Workshop
Bayesian learning theory for complex data modelling Workshop, Sep 2018, Grenoble, France. pp.1

International audience

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::eb29fde9828031f5c63cf0a1b8ae63f3
https://hal.archives-ouvertes.fr/hal-01950663/file/datasafe.pdf

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání