ECG Monitoring in Wearable Devices by Sparse Models

Carrera, Diego; Rossi, Beatrice; Zambon, Daniele; Fragneto, Pasqualina; Boracchi, Giacomo

doi:10.1007/978-3-319-46131-1_21

Cited by 9 publications

(17 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper we consider dictionaries yielding sparse representations as datadriven models to detect anomalous heartbeats, and describe a practical domainadaptation solution that allows monitoring at different heart rates. Dictionaries yielding sparse representations are one of the leading models in image and signal processing [33,34], and have been also fruitfully used in many machine learning scenarios such as face recognition [35,36], abnormal event detection in videos [37], as well as anomaly detection in ECG signals [15,38]. Domain adaptation techniques for dictionaries have been also widely investigated, mainly to address the image classification tasks [39,40,41,42], and go under the name of dictionary adaptation.…”

Section: Related Workmentioning

confidence: 99%

“…We consider the simple, yet effective, anomaly-detection algorithm [15] presented in Algorithm 1, where normal heartbeats are modeled by means of a user-specific dictionary. The dictionary D u,r0 ∈ R p(r0)×n and the sparsity level…”

Section: Online Anomaly Detection In Ecg Signalsmentioning

confidence: 99%

“…As such, to successfully classify or detect anomalies in ECG signals, a single data-driven model is not able to accurately describe all the users (even when trained on large datasets), and has to be directly learned / customized from the heartbeats of the specific user [6,7]. In a wearabledevice scenario, where the user places the device by himself, this training / customization of the data-driven model has to be performed every time the device is placed, since heartbeats acquired from the same user and device exhibit a different morphology when the device position changes [15,14].…”

Section: Introductionmentioning

confidence: 99%

“…This paper extends [15], which presents the algorithm for detecting anomalous heartbeats, [22] which introduces dictionary adaptation and [21] and describes the user-configuration phase that to be run every time the device is placed. Section 7 presents our experimental campaign, and conclusions are drawn in Section 8.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Online anomaly detection for long-term ECG monitoring using wearable devices

Carrera

Rossi

Fragneto

et al. 2019

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Many successful algorithms for analyzing ECG signals leverage data-driven models that are learned for each specific user. Unfortunately, a few algorithmic challenges are still to be addressed before employing these models in wearable devices, thus enabling online and long-term monitoring. In particular, since the heartbeats morphology changes with the heart rate, models learned in resting conditions need to be adapted to analyze ECG signals recorded during everyday activities. We propose an online ECG monitoring solution where normal heartbeats of each specific user are modeled by dictionaries yielding sparse representations, and heartbeats that do not conform to this model are detected as anomalous. We track heart rate variations by adapting the user-specific dictionary with a set of user-independent, linear, transformations. Our experiments demonstrate that these transformations can be successfully learned from a public dataset of ECG signals and that, thanks to an optimized anomaly-detection algorithm, our solution enables online and long-term ECG monitoring.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Online Anomaly Detection In Ecg Signalsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Online anomaly detection for long-term ECG monitoring using wearable devices

Carrera

Rossi

Fragneto

et al. 2019

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…In case of ECG monitoring, the data to be analyzed are the heartbeats, that are extracted from the ECG signal using traditional algorithms. Since our goal is to perform ECG monitoring directly on the wearable device, that has limited computational capabilities, we adopt a different sparse coding procedure, that is based on the 0 "norm" and it is performed by means of greedy algorithms [11]. In particular, we proposed a novel variant of the OMP algorithm [9], that is specifically designed for dictionary D ∈ R d×n where n < d, that is settings we adopt in ECG monitoring.…”

Section: Sparsity-based Anomaly Detectionmentioning

confidence: 99%

Learning and Adaptation to Detect Changes and Anomalies in High-Dimensional Data

Carrera

2019

Special Topics in Information Technology

Self Cite

View full text Add to dashboard Cite

The problem of monitoring a datastream and detecting whether the data generating process changes from normal to novel and possibly anomalous conditions has relevant applications in many real scenarios, such as health monitoring and quality inspection of industrial processes. A general approach often adopted in the literature is to learn a model to describe normal data and detect as anomalous those data that do not conform to the learned model. However, several challenges have to be addressed to make this approach effective in real world scenarios, where acquired data are often characterized by high dimension and feature complex structures (such as signals and images). We address this problem from two perspectives corresponding to different modeling assumptions on the data-generating process. At first, we model data as realization of random vectors, as it is customary in the statistical literature. In this settings we focus on the change detection problem, where the goal is to detect whether the datastream permanently departs from normal conditions. We theoretically prove the intrinsic difficulty of this problem when the data dimension increases and propose a novel non-parametric and multivariate change-detection algorithm. In the second part, we focus on data having complex structure and we adopt dictionaries yielding sparse representations to model normal data. We propose novel algorithms to detect anomalies in such datastreams and to adapt the learned model when the process generating normal data changes.

show abstract

UniMAP: model-free detection of unclassified noise transients in LIGO-Virgo data using the temporal outlier factor

Ding

McIver

2022

Class. Quantum Grav.

View full text Add to dashboard Cite

Data from current gravitational wave detectors contains a high rate of transient noise (glitches) that can trigger false detections and obscure true astrophysical events. Existing noise-detection algorithms largely rely on model-based methods that may miss noise transients unwitnessed by auxiliary sensors or with exotic morphologies. We propose the Unicorn Multi-window Anomaly-detection Pipeline (UniMAP): a model-free algorithm to identify and characterize transient noise leveraging the Temporal Outlier Factor (TOF) via a multi-window data-resampling scheme. We show this windowing scheme extends the anomaly detection capabilities of the TOF algorithm to resolve noise transients of arbitrary morphology and duration. We demonstrate the eﬃcacy of this pipeline in detecting glitches during LIGO and Virgo’s third observing run, and discuss potential applications.

show abstract

ECG Monitoring in Wearable Devices by Sparse Models

Cited by 9 publications

References 22 publications

Online anomaly detection for long-term ECG monitoring using wearable devices

Online anomaly detection for long-term ECG monitoring using wearable devices

Learning and Adaptation to Detect Changes and Anomalies in High-Dimensional Data

UniMAP: model-free detection of unclassified noise transients in LIGO-Virgo data using the temporal outlier factor

Contact Info

Product

Resources

About