Investigation of Fault-Tolerant Adaptive Filtering for Noisy ECG Signals

Abstract

Studies shows that Electrocardiogram (ECG) computer programs perform at least equally well as human observers in ECG measurement and coding, and can replace the cardiologist in epidemiological studies and clinical trials [1]. However, in order to also replace the cardiologist in clinical settings, such as for out-patients, better systems are required in order to reduce ambient noise while maintaining signal sensitivity. Therefore the objective of this work was to develop an adaptive filter to remove the contaminating signal in order to better obtain and interpret the electrocardiogram (ECG) data. To achieve reliability, the real-time computing systems must be fault-tolerant. This paper proposed a fault-tolerant adaptive filter for noise cancellation of ECG signals. Comparison of the performance and reliability of non-fault-tolerant and fault-tolerant adaptive filters are performed. Experimental results showed that the fault-tolerant adaptive filter not only successfully extract the ECG signals, but also is very reliable.

Fault mitigation strategies for CUDA GPUs

“…We will therefore assume that a Faulty SM Map (FM), indicating Paper 8. 3 INTERNATIONAL TEST CONFERENCE 2 The instrumented kernel avoids the execution of thread blocks on faulty SMs. Since this task cannot be performed by directly operating on the Block Dispatcher (the CUDA-ISA does not provide this functionality), an ad-hoc procedure must be implemented.…”

“…In fact, each faulty SM must be able to execute the while loop, to perform the atomic subtraction, Paper 8. 3 INTERNATIONAL TEST CONFERENCE 6 …”

“…Nowadays, automotive [1], space [2] and medical [3] applications are characterized by an increasing reliance on intelligent control and safety. The robustness of a system, i.e., its ability to continue to function despite the existence of faults, even if system performance may be diminished or altered, is often enhanced by fault-tolerance or fault mitigation techniques.…”