Optimization and Deployment of Deep Neural Networks for PPG-based Blood Pressure Estimation Targeting Low-power Wearables

• URL: http://arxiv.org/abs/2409.07485v1
• Date: Tue, 3 Sep 2024 15:48:43 GMT
• Title: Optimization and Deployment of Deep Neural Networks for PPG-based Blood Pressure Estimation Targeting Low-power Wearables
• Authors: Alessio Burrello, Francesco Carlucci, Giovanni Pollo, Xiaying Wang, Massimo Poncino, Enrico Macii, Luca Benini, Daniele Jahier Pagliari,
• Abstract summary: State-of-the-art Deep Neural Networks (DNNs) trained for a PPG-to-BP signal-to-signal reconstruction or a scalar BP value regression have been shown to outperform classic methods on public datasets. We describe a fully-automated DNN design pipeline, encompassing HW-aware Neural Architecture Search (NAS) and Quantization, that can be deployed on an ultra-low-power System-on-Chip (SoC), GAP8.
• Score: 18.038842995948034
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: PPG-based Blood Pressure (BP) estimation is a challenging biosignal processing task for low-power devices such as wearables. State-of-the-art Deep Neural Networks (DNNs) trained for this task implement either a PPG-to-BP signal-to-signal reconstruction or a scalar BP value regression and have been shown to outperform classic methods on the largest and most complex public datasets. However, these models often require excessive parameter storage or computational effort for wearable deployment, exceeding the available memory or incurring too high latency and energy consumption. In this work, we describe a fully-automated DNN design pipeline, encompassing HW-aware Neural Architecture Search (NAS) and Quantization, thanks to which we derive accurate yet lightweight models, that can be deployed on an ultra-low-power multicore System-on-Chip (SoC), GAP8. Starting from both regression and signal-to-signal state-of-the-art models on four public datasets, we obtain optimized versions that achieve up to 4.99% lower error or 73.36% lower size at iso-error. Noteworthy, while the most accurate SoA network on the largest dataset can not fit the GAP8 memory, all our optimized models can; our most accurate DNN consumes as little as 0.37 mJ while reaching the lowest MAE of 8.08 on Diastolic BP estimation.

Related papers

• Network architecture search of X-ray based scientific applications [4.8287663496299755]
  X-ray and electron diffraction-based microscopy use bragg peak detection and ptychography to perform 3-D imaging at an atomic resolution. Recently, the use of deep neural networks has improved the existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-04-16T16:09:38Z)
• NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes [52.51014498593644]
  Deep neural networks (DNNs) have become ubiquitous in machine learning, but their energy consumption remains a notable issue. We introduce NeuralFuse, a novel add-on module that addresses the accuracy-energy tradeoff in low-voltage regimes. At a 1% bit error rate, NeuralFuse can reduce memory access energy by up to 24% while recovering accuracy by up to 57%.
  arXiv  Detail & Related papers  (2023-06-29T11:38:22Z)
• PPG-based Heart Rate Estimation with Efficient Sensor Sampling and Learning Models [6.157700936357335]
  Photoplethysthy (mography) sensors embedded in wearable devices can estimate heart rate (HR) with high accuracy. However, applying PPG sensor based HR estimation to embedded devices still faces challenges due to the energy-intensive high-frequency PPG sampling. In this work, we aim to explore HR estimation techniques that are more suitable for lower-power and resource-constrained embedded devices.
  arXiv  Detail & Related papers  (2023-03-23T19:47:36Z)
• A Meta-Learning Approach to Predicting Performance and Data Requirements [163.4412093478316]
  We propose an approach to estimate the number of samples required for a model to reach a target performance. We find that the power law, the de facto principle to estimate model performance, leads to large error when using a small dataset. We introduce a novel piecewise power law (PPL) that handles the two data differently.
  arXiv  Detail & Related papers  (2023-03-02T21:48:22Z)
• Atrial Fibrillation Detection Using Weight-Pruned, Log-Quantised Convolutional Neural Networks [25.160063477248904]
  A convolutional neural network model is developed for detecting atrial fibrillation from electrocardiogram signals. The model demonstrates high performance despite being trained on limited, variable-length input data. The final model achieved a 91.1% model compression ratio while maintaining high model accuracy of 91.7% and less than 1% loss.
  arXiv  Detail & Related papers  (2022-06-14T11:47:04Z)
• Q-PPG: Energy-Efficient PPG-based Heart Rate Monitoring on Wearable Devices [22.7371904884504]
  We propose a design methodology to automatically generate a rich family of deep Temporal Convolutional Networks (TCNs) for HR monitoring. Our most accurate model sets a new state-of-the-art in Mean Absolute Error. We deploy our TCNs on an embedded platform featuring a STM32WB55 microcontroller, demonstrating their suitability for real-time execution.
  arXiv  Detail & Related papers  (2022-03-24T10:50:33Z)
• BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing [48.11023234245863]
  We propose a new framework called BottleFit, which includes a novel training strategy to achieve high accuracy even with strong compression rates. BottleFit achieves 77.1% data compression with up to 0.6% accuracy loss on ImageNet dataset. We show that BottleFit decreases power consumption and latency respectively by up to 49% and 89% with respect to (w.r.t.) local computing and by 37% and 55% w.r.t. edge offloading.
  arXiv  Detail & Related papers  (2022-01-07T22:08:07Z)
• LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time [57.52251547365967]
  We propose a method for training a "compressible subspace" of neural networks that contains a fine-grained spectrum of models. We present results for achieving arbitrarily fine-grained accuracy-efficiency trade-offs at inference time for structured and unstructured sparsity. Our algorithm extends to quantization at variable bit widths, achieving accuracy on par with individually trained networks.
  arXiv  Detail & Related papers  (2021-10-08T17:03:34Z)
• ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models [56.21470608621633]
  We propose a time estimation framework to decouple the architectural search from the target hardware. The proposed methodology extracts a set of models from micro- kernel and multi-layer benchmarks and generates a stacked model for mapping and network execution time estimation. We compare estimation accuracy and fidelity of the generated mixed models, statistical models with the roofline model, and a refined roofline model for evaluation.
  arXiv  Detail & Related papers  (2021-05-07T11:39:05Z)
• Fast convolutional neural networks on FPGAs with hls4ml [0.22756183402372013]
  We introduce an automated tool for deploying ultra low-latency, low-power deep neural networks on FPGAs. We demonstrate how to achieve inference latency of $5,mu$s using convolutional architectures, while preserving state-of-the-art model performance.
  arXiv  Detail & Related papers  (2021-01-13T14:47:11Z)
• HiPPO: Recurrent Memory with Optimal Polynomial Projections [93.3537706398653]
  We introduce a general framework (HiPPO) for the online compression of continuous signals and discrete time series by projection onto bases. Given a measure that specifies the importance of each time step in the past, HiPPO produces an optimal solution to a natural online function approximation problem. This formal framework yields a new memory update mechanism (HiPPO-LegS) that scales through time to remember all history, avoiding priors on the timescale.
  arXiv  Detail & Related papers  (2020-08-17T23:39:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.