Improving kernel-energy trade-offs for machine learning in implantable and wearable biomedical applications

Emerging biomedical sensors and stimulators offer unprecedented modalities for delivering therapy and acquiring physiological signals (e.g., deep brain stimulators). Exploiting these in intelligent, closedloop systems requires detecting specific physiological states using very low power (i.e., 1-10mW for wearable devices, 10-100 W for implantable devices). Machine learning is a powerful tool for modeling correlations in physiological signals, but model complexity in typical biomedical applications makes detection too computationally intensive. We analyze the computational energy trade-offs and propose a method of restructuring the computations to yield more favorable trade-offs, especially for typical biomedical applications. We thus develop a methodology for implementing low-energy classification kernels and demonstrate energy reduction in practical biomedical systems. Two applications, arrhythmia detection using electrocardiographs (ECG) from the MIT-BIH database [1] and seizure det...

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Kyong-Ho Lee, Sun-Yuan Kung, Naveen Verma
• Keywords: Biomedical, ICASSP 2011, Physiological Signals, Signal Processing, Typical Biomedical Applications