No abstract

No abstract

Abstract-In this paper, an algorithm for breathing rate extraction from PPG signal is proposed. Two critical aspects have been endorsed during the implementation: i) good performances and ii) low computational complexity. The proposed solution is based on the Empirical Mode Decomposition (EMD) approach and it proves to be robust and accurate even in presence of noisy epochs. It has been validated on two distinct datasets: a)experimental data we have collected using wearables for physiological monitoring and b) recording sessions from PhysioBank MIMIC II Waveform Database. The presented results showed a mean absolute error of 0.0044 Hz, corresponding to 0.26 breaths per minute.

Modern Convolutional Neural Networks (CNNs) are typically based on floating point linear algebra based implementations. Recently, reduced precision Neural Networks (NNs) have been gaining popularity as they require significantly less memory and computational resources compared to floating point. This is particularly important in power constrained compute environments. However, in many cases a reduction in precision comes at a small cost to the accuracy of the resultant network. In this work, we investigate the accuracy-throughput trade-off for various parameter precision applied to different types of NN models. We firstly propose a quantization training strategy that allows reduced precision NN inference with a lower memory footprint and competitive model accuracy. Then, we quantitatively formulate the relationship between data representation and hardware efficiency. Our experiments finally provide insightful observation. For example, one of our tests show 32-bit floating point is more hardware efficient than 1-bit parameters to achieve 99% MNIST accuracy. In general, 2-bit and 4-bit fixed point parameters show better hardware trade-off on small-scale datasets like MNIST and CIFAR-10 while 4-bit provide the best trade-off in large-scale tasks like AlexNet on ImageNet dataset within our tested problem domain.

Traditionally, hypervisors, operating systems, and runtime systems have been providing an abstraction layer over the bare-metal hardware. Traditional abstractions, however, do not consider for nonfunctional requirements such as system-level constraints or users' objectives. As these requirements are gaining increasing importance, researchers are looking into making user-specified and systemlevel objectives first-class citizens in the computer systems' realm.This paper describes the Autonomic Operating System (AcOS) project; AcOS enhances commodity operating systems with an autonomic layer that enables self-* properties through adaptive resource allocation. With AcOS, we investigate intelligent resource allocation to achieve user-specified service-level objectives on application performance and to respect system-level thresholds on CPU temperature. We give a broad overview of AcOS, elaborate on its achievements, and discuss research perspectives.