Flexible Analog-to-Feature converter for wireless smart healthcare sensors - Télécom Paris Access content directly
Conference Papers Year : 2023

Flexible Analog-to-Feature converter for wireless smart healthcare sensors

Abstract

Analog-to-Feature (A2F) conversion based on Non-Uniform Wavelet Sampling (NUWS) has demonstrated the ability to drastically reduce the energy consumption in wireless sensors while employed for electrocardiogram (ECG) anomaly detection. The underlying idea is to extract relevant features from the analog signal and perform the classification in the digital domain. We adopt the same approach for a human activity recognition (HAR) task, considered as a second application for a proposed generic A2F converter. By extracting only 16 features from the inertial signals of the UCI-HAR data set and using these features as inputs for a simple Neural Network, we achieved an 87.7% accuracy in multiclass classification. From the simulation results, we defined the relevant features and the hardware specifications required for a complete circuit design and chip fabrication.
Fichier principal
Vignette du fichier
NEWCAS2023_Flexible_Analog-to-Feature_Converter_for_Wireless_Smart_Healthcare_Sensors.pdf (323.41 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04155396 , version 1 (07-07-2023)
hal-04155396 , version 2 (20-07-2023)

Identifiers

  • HAL Id : hal-04155396 , version 2

Cite

Mikhail Manokhin, Paul Chollet, Patricia Desgreys. Flexible Analog-to-Feature converter for wireless smart healthcare sensors. 21st IEEE Interregional NEWCAS 2023 Conference, Jun 2023, Edinburgh, United Kingdom. ⟨hal-04155396v2⟩
61 View
37 Download

Share

Gmail Mastodon Facebook X LinkedIn More