Feature selection algorithms for flexible analog-to-feature converter - Equipe Circuits et Systèmes de Communications Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Feature selection algorithms for flexible analog-to-feature converter

Résumé

One of the main challenges in the field of wireless sensors is to increase their battery life. Analog-to-feature (A2F) conversion is an acquisition method thought for IoT devices, that perform classification tasks at sub-Nyquist rate, by extracting relevant features in the analog domain and then performing the classification step in the digital domain. Current A2F solutions are designed for a specific application, this paper proposes a method to design a generic A2F converter usable for several signal types. In order to extract information for classification task, we propose to use non uniform wavelet sampling, its drawback is that it brings redundancy and irrelevant information. To reach our goal of decreasing power consumption, we need to extract a small set of relevant features for classification. To achieve this, several features selection algorithms are tested for electrocardiogram (ECG) anomalies detection. We demonstrate that the detection rate of ECG anomalies can reach 98% with less than 10 features extracted.
Fichier non déposé

Dates et versions

hal-02927208 , version 1 (01-09-2020)

Identifiants

Citer

Antoine Back, Paul Chollet, Olivier Fercoq, Patricia Desgreys. Feature selection algorithms for flexible analog-to-feature converter. 2020 18th IEEE International New Circuits and Systems Conference (NEWCAS), Jun 2020, Montréal, Canada. pp.186-189, ⟨10.1109/NEWCAS49341.2020.9159817⟩. ⟨hal-02927208⟩
49 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More