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

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.