Tailoring SVM Inference for Resource-Efficient ECG-Based Epilepsy Monitors

Lorenzo Ferretti1, Amir Aminifar2, David Atienza2, Leila Cammoun3 and Philippe Ryvlin3
1Giovanni Ansaloni, Laura Pozzi, Università della Svizzera Italiana, Lugano, Switzerland
2Embedded Systems Laboratory, EPFL, Lausanne, Switzerland
3Département des Neurosciences Cliniques, Centre Hospitalier Universitaire Vaudois, Lausanne, Switzerland

ABSTRACT


Event detection and classification algorithms are resilient towards aggressive resource-aware optimisations. In this paper, we leverage this characteristic in the context of smart health monitoring systems. In more detail, we study the attainable benefits resulting from tailoring Support Vector Machine (SVM) inference engines devoted to the detection of epileptic seizures from ECG-derived features. We conceive and explore multiple optimisations, each effectively reducing resource budgets while minimally impacting classification performance. These strategies can be seamlessly combined, which results in 12.5X and 16X gains in energy and area, respectively, with a negligible loss, 3.2% in classification performance.

Keywords: Wireless Body Sensor Nodes, Seizure detection, Ultra-low-power design, Algorithmic optimisation.



Full Text (PDF)