Flexible Analog-to-Feature Converter for Wireless Smart Healthcare Sensors

Mikhail Manokhin; Paul Chollet; Patricia Desgreys

doi:10.1109/NEWCAS57931.2023.10198150

Flexible Analog-to-Feature Converter for Wireless Smart Healthcare Sensors

Mikhail Manokhin
, Paul Chollet
, Patricia Desgreys

Institut Polytechnique de Paris

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

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.

Original language	English
Title of host publication	21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350300246
DOIs	https://doi.org/10.1109/NEWCAS57931.2023.10198150
Publication status	Published - 1 Jan 2023
Event	21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 - Edinburgh, United Kingdom Duration: 26 Jun 2023 → 28 Jun 2023

Publication series

Name	21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 - Proceedings

Conference

Conference	21st IEEE Interregional NEWCAS Conference, NEWCAS 2023
Country/Territory	United Kingdom
City	Edinburgh
Period	26/06/23 → 28/06/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Analog-to-Feature converter
Human activity recognition
Non-Uniform Wavelet Sampling
Smart sensors

Access to Document

10.1109/NEWCAS57931.2023.10198150

Cite this

Manokhin, M., Chollet, P., & Desgreys, P. (2023). Flexible Analog-to-Feature Converter for Wireless Smart Healthcare Sensors. In 21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 - Proceedings (21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NEWCAS57931.2023.10198150

@inproceedings{80d084cd3cbe45f683d38067949c427a,

title = "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.",

keywords = "Analog-to-Feature converter, Human activity recognition, Non-Uniform Wavelet Sampling, Smart sensors",

author = "Mikhail Manokhin and Paul Chollet and Patricia Desgreys",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 ; Conference date: 26-06-2023 Through 28-06-2023",

year = "2023",

month = jan,

day = "1",

doi = "10.1109/NEWCAS57931.2023.10198150",

language = "English",

series = "21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 - Proceedings",

}

Manokhin, M, Chollet, P & Desgreys, P 2023, Flexible Analog-to-Feature Converter for Wireless Smart Healthcare Sensors. in 21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 - Proceedings. 21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 21st IEEE Interregional NEWCAS Conference, NEWCAS 2023, Edinburgh, United Kingdom, 26/06/23. https://doi.org/10.1109/NEWCAS57931.2023.10198150

Flexible Analog-to-Feature Converter for Wireless Smart Healthcare Sensors. / Manokhin, Mikhail; Chollet, Paul ; Desgreys, Patricia.
21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. (21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Flexible Analog-to-Feature Converter for Wireless Smart Healthcare Sensors

AU - Manokhin, Mikhail

AU - Chollet, Paul

AU - Desgreys, Patricia

PY - 2023/1/1

Y1 - 2023/1/1

N2 - 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.

AB - 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.

KW - Analog-to-Feature converter

KW - Human activity recognition

KW - Non-Uniform Wavelet Sampling

KW - Smart sensors

U2 - 10.1109/NEWCAS57931.2023.10198150

DO - 10.1109/NEWCAS57931.2023.10198150

M3 - Conference contribution

AN - SCOPUS:85168553009

T3 - 21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 - Proceedings

BT - 21st IEEE Interregional NEWCAS Conference, NEWCAS 2023 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 21st IEEE Interregional NEWCAS Conference, NEWCAS 2023

Y2 - 26 June 2023 through 28 June 2023

ER -

Flexible Analog-to-Feature Converter for Wireless Smart Healthcare Sensors

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this