Skip to Main content Skip to Navigation
Conference papers

Analog-to-feature converter optimization through power-aware feature selection

Abstract : Analog-to-feature (A2F) conversion is an acquisition method thought for IoT devices in order to increase wireless sensor's battery life. The operating principle of A2F is to 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. We propose to use non-uniform wavelet sampling (NUWS) combined with feature selection to find and extract from the signal, a small set of relevant features for electrocardiogram (ECG) anomalies detection. A CMOS 0.18 µm m mixed architecture for NUWS feature extraction is proposed, to obtain a power consumption model for A2F. This model can be taken into account in the feature selection step by evaluating the energy cost of each wavelet and then try to maximize classification accuracy while minimizing the energy needed for extraction. We demonstrate the benefits of A2F showing that the energy needed can be divided by 16 compared to classical approach.
Complete list of metadata
Contributor : Antoine BACK Connect in order to contact the contributor
Submitted on : Wednesday, October 13, 2021 - 2:44:26 PM
Last modification on : Monday, January 17, 2022 - 2:28:01 PM


Files produced by the author(s)


  • HAL Id : hal-03329932, version 2


Antoine Back, Paul Chollet, Olivier Fercoq, Patricia Desgreys. Analog-to-feature converter optimization through power-aware feature selection. International Conference on Analog VLSI Circuits, Oct 2021, Bordeaux, France. ⟨hal-03329932v2⟩



Record views


Files downloads