TY - GEN
T1 - Flexible Analog-to-Feature Converter for Wireless Smart Healthcare Sensors
AU - Manokhin, Mikhail
AU - Chollet, Paul
AU - Desgreys, Patricia
N1 - Publisher Copyright:
© 2023 IEEE.
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 -
