SCG With Your Phone: Diagnosis of Rhythmic Spectrum Disorders in Field Conditions

• URL: http://arxiv.org/abs/2601.13926v1
• Date: Tue, 20 Jan 2026 12:58:31 GMT
• Title: SCG With Your Phone: Diagnosis of Rhythmic Spectrum Disorders in Field Conditions
• Authors: Peter Golenderov, Yaroslav Matushenko, Anastasia Tushina, Michal Barodkin,
• Abstract summary: We present a robust deep-learning framework for SCG segmentation and rhythm analysis using accelerometer recordings obtained with consumer smartphones.<n>We develop an enhanced U-Net v3 architecture that integrates multi-scale convolutions, residual connections, and attention gates.<n>A dedicated post-processing pipeline converts probability masks into precise AO timestamps, whereas a novel adaptive 3D-to-1D projection method ensures robustness to arbitrary smartphone orientation.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Aortic valve opening (AO) events are crucial for detecting frequency and rhythm disorders, especially in real-world settings where seismocardiography (SCG) signals collected via consumer smartphones are subject to noise, motion artifacts, and variability caused by device heterogeneity. In this work, we present a robust deep-learning framework for SCG segmentation and rhythm analysis using accelerometer recordings obtained with consumer smartphones. We develop an enhanced U-Net v3 architecture that integrates multi-scale convolutions, residual connections, and attention gates, enabling reliable segmentation of noisy SCG signals. A dedicated post-processing pipeline converts probability masks into precise AO timestamps, whereas a novel adaptive 3D-to-1D projection method ensures robustness to arbitrary smartphone orientation. Experimental results demonstrate that the proposed method achieves consistently high accuracy and robustness across various device types and unsupervised data-collection conditions. Our approach enables practical, low-cost, and automated cardiac-rhythm monitoring using everyday mobile devices, paving the way for scalable, field-deployable cardiovascular assessment and future multimodal diagnostic systems.

Related papers

• A Sensing Dataset Protocol for Benchmarking and Multi-Task Wireless Sensing [45.99328292838584]
  We propose the Sensing dataset Protocol (SDP), a protocol-level specification and benchmark framework for large-scale wireless sensing.<n>SDP defines how heterogeneous wireless signals are mapped into a unified perception data-block schema.<n>A unified benchmark is established for detection, recognition, and vital-sign estimation with consistent preprocessing, training, and evaluation.
  arXiv  Detail & Related papers  (2025-12-13T05:01:30Z)
• Enhancing ECG Classification Robustness with Lightweight Unsupervised Anomaly Detection Filters [39.9470953186283]
  Continuous electrocardiogram (ECG) monitoring via wearables offers significant potential for early cardiovascular disease (CVD) detection.<n> deploying deep learning models for automated analysis in resource-constrained environments faces reliability challenges due to Out-of-Distribution data.<n>This paper explores Unsupervised Anomaly Detection (UAD) as an independent, upstream filtering mechanism to improve robustness.
  arXiv  Detail & Related papers  (2025-10-30T13:54:37Z)
• Prototyping an End-to-End Multi-Modal Tiny-CNN for Cardiovascular Sensor Patches [35.899401205042615]
  We propose a convolutional neural network with early fusion of data to solve a binary classification problem.<n>Our approach reduces memory footprint and compute cost by three orders of magnitude compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2025-10-21T14:23:20Z)
• Versatile Cardiovascular Signal Generation with a Unified Diffusion Transformer [41.095491708125515]
  We propose UniCardio, a multi-modal diffusion transformer that reconstructs low-quality signals and synthesizes unrecorded signals.<n>By exploiting the complementary nature of cardiovascular signals, UniCardio clearly outperforms recent task-specific baselines in signal denoising, imputation, and translation.<n>These advantages position UniCardio as a promising avenue for advancing AI-assisted healthcare.
  arXiv  Detail & Related papers  (2025-05-28T12:45:39Z)
• Evaluating ML Robustness in GNSS Interference Classification, Characterization & Localization [42.14439854721613]
  Jamming devices disrupt signals from the global navigation satellite system (GNSS)<n>This paper introduces an extensive dataset comprising snapshots obtained from a low-frequency antenna.<n>Our objective is to assess the resilience of machine learning (ML) models against environmental changes.
  arXiv  Detail & Related papers  (2024-09-23T15:20:33Z)
• Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective [40.21603048003118]
  Variational Autoencoders (VAEs) have gained popularity in recent decades due to their superior de-noising capabilities. FCVAE exploits an innovative approach to concurrently integrate both the global and local frequency features into the condition of Conditional Variational Autoencoder (CVAE) Our approach has been evaluated on public datasets and a large-scale cloud system, and the results demonstrate that it outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-02-05T09:06:57Z)
• Enhancing ECG Analysis of Implantable Cardiac Monitor Data: An Efficient Pipeline for Multi-Label Classification [0.0]
  Implantable Cardiac Monitor (ICM) devices are demonstrating as of today, the fastest-growing market for implantable cardiac devices. ICMs constantly monitor and record a patient's heart rhythm and when triggered - send it to a secure server where health care professionals can review it. This study presents the challenges and solutions in automatically analyzing ICM data and introduces a method for its classification that outperforms existing methods on such data.
  arXiv  Detail & Related papers  (2023-07-12T12:49:18Z)
• Deep Learning-Based Arrhythmia Detection Using RR-Interval Framed Electrocardiograms [9.884633954053344]
  Deep learning can be used to achieve personal authentication in biometric security applications. We developed a model for the detection of arrhythmia in which time-sliced ECG data represents the distance between successive R-peaks. This compact system can be implemented in wearable devices or real-time monitoring equipment.
  arXiv  Detail & Related papers  (2020-12-01T09:10:24Z)
• Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approach [40.992167455141946]
  This paper proposes a new communication-efficient on-device federated learning (FL)-based deep anomaly detection framework for sensing time-series data in IIoT. We first introduce a FL framework to enable decentralized edge devices to collaboratively train an anomaly detection model, which can improve its generalization ability. Second, we propose an Attention Mechanism-based Convolutional Neural Network-Long Short Term Memory (AMCNN-LSTM) model to accurately detect anomalies. Third, to adapt the proposed framework to the timeliness of industrial anomaly detection, we propose a gradient compression mechanism based on Top-textitk selection to
  arXiv  Detail & Related papers  (2020-07-19T16:47:26Z)
• A Graph-constrained Changepoint Detection Approach for ECG Segmentation [5.209323879611983]
  We introduce a novel graph-based optimal changepoint detection (GCCD) method for reliable detection of R-peak positions without employing any preprocessing step. Based on the MIT-BIH arrhythmia (MIT-BIH-AR) database, the proposed method achieves overall sensitivity Sen = 99.76, positive predictivity PPR = 99.68, and detection error rate DER = 0.55.
  arXiv  Detail & Related papers  (2020-04-24T23:41:41Z)
• DeepBeat: A multi-task deep learning approach to assess signal quality and arrhythmia detection in wearable devices [0.0]
  We develop a multi-task deep learning method to assess signal quality and arrhythmia event detection in wearable photoplethysmography devices for real-time detection of atrial fibrillation (AF) We train our algorithm on over one million simulated unlabeled physiological signals and fine-tune on a curated dataset of over 500K labeled signals from over 100 individuals from 3 different wearable devices. We show that two-stage training can help address the unbalanced data problem common to biomedical applications where large well-annotated datasets are scarce.
  arXiv  Detail & Related papers  (2020-01-01T07:41:28Z)

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.