Tiny-HR: Towards an interpretable machine learning pipeline for heart rate estimation on edge devices

• URL: http://arxiv.org/abs/2208.07981v1
• Date: Tue, 16 Aug 2022 22:38:10 GMT
• Title: Tiny-HR: Towards an interpretable machine learning pipeline for heart rate estimation on edge devices
• Authors: Preetam Anbukarasu, Shailesh Nanisetty, Ganesh Tata and Nilanjan Ray
• Abstract summary: This paper is a proof of concept, machine learning (ML) pipeline that extracts heart rate from pressure sensor data acquired on low-power edge devices. The pipeline consists an upsampler neural network, a signal quality classifier, and a 1D-convolutional neural network optimized for efficient and accurate heart rate estimation. The results indicate that the proposed ML and hybrid pipeline reduces energy and time per inference by 82% and 28% compared to traditional algorithms.
• Score: 6.59529078336196
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The focus of this paper is a proof of concept, machine learning (ML) pipeline that extracts heart rate from pressure sensor data acquired on low-power edge devices. The ML pipeline consists an upsampler neural network, a signal quality classifier, and a 1D-convolutional neural network optimized for efficient and accurate heart rate estimation. The models were designed so the pipeline was less than 40 kB. Further, a hybrid pipeline consisting of the upsampler and classifier, followed by a peak detection algorithm was developed. The pipelines were deployed on ESP32 edge device and benchmarked against signal processing to determine the energy usage, and inference times. The results indicate that the proposed ML and hybrid pipeline reduces energy and time per inference by 82% and 28% compared to traditional algorithms. The main trade-off for ML pipeline was accuracy, with a mean absolute error (MAE) of 3.28, compared to 2.39 and 1.17 for the hybrid and signal processing pipelines. The ML models thus show promise for deployment in energy and computationally constrained devices. Further, the lower sampling rate and computational requirements for the ML pipeline could enable custom hardware solutions to reduce the cost and energy needs of wearable devices.

Related papers

• Real-Time Human Activity Recognition on Edge Microcontrollers: Dynamic Hierarchical Inference with Multi-Spectral Sensor Fusion [7.184610830886172]
  We propose a resource-aware hierarchical network based on multi-spectral fusion and interpretable modules.<n> Deployed on an ARM Cortex-M4 microcontroller for low-power real-time inference, HPPI-Net achieves 96.70% accuracy.<n>Compared with MobileNetV3, HPPI-Net improves accuracy by 1.22% and reduces RAM usage by 71.2% and ROM usage by 42.1%.
  arXiv  Detail & Related papers  (2026-01-29T15:21:45Z)
• Efficient and Accurate Downfacing Visual Inertial Odometry [18.91672527573445]
  This paper presents an efficient and accurate VIO pipeline optimized for applications on micro- and nano-UAVs.<n>The proposed design incorporates state-of-the-art feature detection and tracking methods, all optimized and quantized for emerging RISC-V-based ultra-low-power parallel systems.
  arXiv  Detail & Related papers  (2025-09-12T07:30:24Z)
• Architectural Exploration of Hybrid Neural Decoders for Neuromorphic Implantable BMI [5.76010717601678]
  This work presents an efficient decoding pipeline for neuromorphic implantable brain-machine interfaces (Neu-iBMI)<n>We introduce a tunable event filter (EvFilter), which also functions as a spike detector (EvFilter-SPD), significantly reducing the number of events processed for decoding by 192X and 554X, respectively.
  arXiv  Detail & Related papers  (2025-05-09T12:15:09Z)
• Adaptive Hoeffding Tree with Transfer Learning for Streaming Synchrophasor Data Sets [0.0]
  This paper proposes a transfer learning-based hoeffding tree with ADWIN (THAT) method to detect anomalous synchrophasor signatures. The proposed algorithm is trained and tested with the OzaBag method.
  arXiv  Detail & Related papers  (2025-01-19T21:10:01Z)
• Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance [68.8204255655161]
  We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We evaluate our algorithm across multiple quantized models that we train for different tasks, showing that our approach can reduce the precision of accumulators while maintaining model accuracy with respect to a floating-point baseline.
  arXiv  Detail & Related papers  (2023-01-31T02:46:57Z)
• Implementing Neural Network-Based Equalizers in a Coherent Optical Transmission System Using Field-Programmable Gate Arrays [3.1543509940301946]
  We show the offline FPGA realization of both recurrent and feedforward neural network (NN)-based equalizers for nonlinearity compensation in coherent optical transmission systems. The main results are divided into three parts: a performance comparison, an analysis of how activation functions are implemented, and a report on the complexity of the hardware.
  arXiv  Detail & Related papers  (2022-12-09T07:28:45Z)
• Bayesian Neural Network Language Modeling for Speech Recognition [59.681758762712754]
  State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. In this paper, an overarching full Bayesian learning framework is proposed to account for the underlying uncertainty in LSTM-RNN and Transformer LMs.
  arXiv  Detail & Related papers  (2022-08-28T17:50:19Z)
• Sound Event Classification in an Industrial Environment: Pipe Leakage Detection Use Case [3.9414768019101682]
  A multi-stage Machine Learning pipeline is proposed for pipe leakage detection in an industrial environment. The proposed pipeline applies multiple steps, each addressing the environment's challenges. The results show that the model produces excellent results with 99% accuracy and an F1-score of 0.93 and 0.9 for the respective datasets.
  arXiv  Detail & Related papers  (2022-05-05T15:26:22Z)
• On the Tradeoff between Energy, Precision, and Accuracy in Federated Quantized Neural Networks [68.52621234990728]
  Federated learning (FL) over wireless networks requires balancing between accuracy, energy efficiency, and precision. We propose a quantized FL framework that represents data with a finite level of precision in both local training and uplink transmission. Our framework can reduce energy consumption by up to 53% compared to a standard FL model.
  arXiv  Detail & Related papers  (2021-11-15T17:00:03Z)
• Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining [58.10436813430554]
  Mini-batch training of graph neural networks (GNNs) requires a lot of computation and data movement. We argue in favor of performing mini-batch training with neighborhood sampling in a distributed multi-GPU environment. We present a sequence of improvements to mitigate these bottlenecks, including a performance-engineered neighborhood sampler. We also conduct an empirical analysis that supports the use of sampling for inference, showing that test accuracies are not materially compromised.
  arXiv  Detail & Related papers  (2021-10-16T02:41:35Z)
• Predicting pigging operations in oil pipelines [0.0]
  This paper presents an innovative machine learning methodology to perform automated predictions of the needed pigging operations in crude oil trunklines. Historical pressure signals have been collected by Eni for two years along an oil pipeline (100 km length, 16 inch diameter pipes) located in Northern Italy. A tool has been implemented to automatically highlight the historical pig operations performed on the line.
  arXiv  Detail & Related papers  (2021-09-24T08:49:33Z)
• Bringing AI pipelines onto cloud-HPC: setting a baseline for accuracy of COVID-19 AI diagnosis [5.313553229474047]
  We advocate the StreamFlow Management System as a crucial ingredient to define a parametric pipeline, called "CLAIRE COVID-19 Universal Pipeline" This pipeline is able to explore the optimization methods to classify COVID-19 lung lesions from CT scans, compare them for accuracy, and set a performance baseline. It requires a massive computing power, which is found in traditional HPC infrastructure thanks to the portability-by-design of pipelines designed with StreamFlow.
  arXiv  Detail & Related papers  (2021-08-02T16:45:00Z)
• SignalNet: A Low Resolution Sinusoid Decomposition and Estimation Network [79.04274563889548]
  We propose SignalNet, a neural network architecture that detects the number of sinusoids and estimates their parameters from quantized in-phase and quadrature samples. We introduce a worst-case learning threshold for comparing the results of our network relative to the underlying data distributions. In simulation, we find that our algorithm is always able to surpass the threshold for three-bit data but often cannot exceed the threshold for one-bit data.
  arXiv  Detail & Related papers  (2021-06-10T04:21:20Z)
• Physics and Computing Performance of the Exa.TrkX TrackML Pipeline [0.0]
  This paper documents developments needed to study the physics and computing performance of the Exa.TrkX pipeline. The pipeline achieves tracking efficiency and purity similar to production tracking algorithms.
  arXiv  Detail & Related papers  (2021-03-11T23:10:18Z)
• FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation [81.76975488010213]
  Dense optical flow estimation plays a key role in many robotic vision tasks. Current networks often occupy large number of parameters and require heavy computation costs. Our proposed FastFlowNet works in the well-known coarse-to-fine manner with following innovations.
  arXiv  Detail & Related papers  (2021-03-08T03:09:37Z)

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.