TY - GEN
T1 - A low-energy computation platform for data-driven biomedical monitoring algorithms
AU - Shoaib, Mohammed
AU - Jha, Niraj
AU - Verma, Naveen
PY - 2011
Y1 - 2011
N2 - A key challenge in closed-loop chronic biomedical systems is the ability to detect complex physiological states from patient signals within a constrained power budget. Data-driven machine-learning techniques are major enablers for the modeling and interpretation of such states. Their computational energy, however, scales with the complexity of the required models. In this paper, we propose a low-energy, biomedical computation platform optimized through the use of an accelerator for data-driven classification. The accelerator retains selective flexibility through hardware reconfiguration and exploits voltage scaling and parallelism to operate at a sub-threshold minimum-energy point. Using cardiac arrhythmia detection algorithms with patient data from the MIT-BIH database, classification is achieved in 2.96 μJ (at Vdd = 0.4 V), over four orders of magnitude smaller than that on a low-power general-purpose processor. The energy of feature extraction is 148 μJ while retaining flexibility for a range of possible biomarkers.
AB - A key challenge in closed-loop chronic biomedical systems is the ability to detect complex physiological states from patient signals within a constrained power budget. Data-driven machine-learning techniques are major enablers for the modeling and interpretation of such states. Their computational energy, however, scales with the complexity of the required models. In this paper, we propose a low-energy, biomedical computation platform optimized through the use of an accelerator for data-driven classification. The accelerator retains selective flexibility through hardware reconfiguration and exploits voltage scaling and parallelism to operate at a sub-threshold minimum-energy point. Using cardiac arrhythmia detection algorithms with patient data from the MIT-BIH database, classification is achieved in 2.96 μJ (at Vdd = 0.4 V), over four orders of magnitude smaller than that on a low-power general-purpose processor. The energy of feature extraction is 148 μJ while retaining flexibility for a range of possible biomarkers.
KW - C.3 Real-time and embedded systems
KW - Electrocardiograph (ECG)
KW - support vector machine (SVM)
UR - http://www.scopus.com/inward/record.url?scp=80052685357&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80052685357&partnerID=8YFLogxK
U2 - 10.1145/2024724.2024861
DO - 10.1145/2024724.2024861
M3 - Conference contribution
AN - SCOPUS:80052685357
SN - 9781450306362
T3 - Proceedings - Design Automation Conference
SP - 591
EP - 596
BT - 2011 48th ACM/EDAC/IEEE Design Automation Conference, DAC 2011
PB - Institute of Electrical and Electronics Engineers Inc.
ER -