Antidictionary-Based Cardiac Arrhythmia Classification for Smart ECG Sensors | Duforest, Julien
/5

0 avis

Antidictionary-Based Cardiac Arrhythmia Classification for Smart ECG Sensors

Archive ouverte : Communication dans un congrès

Duforest, Julien | Larras, Benoit | Frappé, Antoine | Deepu, Chacko John | Märtens, Olev

Edité par HAL CCSD ; IEEE

International audience. Cardiovascular diseases can be detected early by analyzing the electrocardiogram of a patient using wearable systems. In the context of smart sensors, detecting arrhythmias with good accuracy and ultra-low power consumption is required for long-term monitoring. This paper presents a novel cardiac arrhythmia classification method based on antidictionaries. The features are sequences of consecutive slopes that are generated from event-driven processing of the input signal. The proposed system shows an average detection accuracy of 98% while offering an ultra-low complexity. This antidictionary-based method is also particularly suited to imbalanced datasets since the antidictionaries are created exclusively from heartbeats classified as normal beats.

Consulter en ligne

Suggestions

Du même auteur

Antidictionary-Based Cardiac Arrhythmia Classification | Duforest, Julien

Antidictionary-Based Cardiac Arrhythmia Classification

Archive ouverte: Communication dans un congrès

Duforest, Julien | 2022-06-27

International audience. Cardiovascular diseases can be detected early by analyzing the electrocardiogram of a patient using wearable systems. In the context of smart sensors, detecting arrhythmias with good accuracy...

Slope-Based Event-Driven Feature Extraction For Cardiac Arrhythmia Classification | Duforest, Julien

Slope-Based Event-Driven Feature Extraction For Cardiac Arrhythmia Classifi...

Archive ouverte: Communication dans un congrès

Duforest, Julien | 2021-10-07

International audience. To detect cardiovascular diseases (CVD), electrocardiogram (ECG) of a patient must be recorded and analyzed for a long period. For an effective diagnosis, the ECG recording system must automa...

Embedded ICG-based Stroke Volume Measurement System: Comparison of Discrete-Time and Continuous-Time Architectures | Gautier, Antoine

Embedded ICG-based Stroke Volume Measurement System: Comparison of Discrete...

Archive ouverte: Communication dans un congrès

Gautier, Antoine | 2021-09-15

International audience. This paper describes the study of an integrated system for the detection of the B-C-X characteristic points of impedance cardiography (ICG) signals, to evaluate the stroke volume of a patient...

Du même sujet

Antidictionary-Based Cardiac Arrhythmia Classification | Duforest, Julien

Antidictionary-Based Cardiac Arrhythmia Classification

Archive ouverte: Communication dans un congrès

Duforest, Julien | 2022-06-27

International audience. Cardiovascular diseases can be detected early by analyzing the electrocardiogram of a patient using wearable systems. In the context of smart sensors, detecting arrhythmias with good accuracy...

Slope-Based Event-Driven Feature Extraction For Cardiac Arrhythmia Classification | Duforest, Julien

Slope-Based Event-Driven Feature Extraction For Cardiac Arrhythmia Classifi...

Archive ouverte: Communication dans un congrès

Duforest, Julien | 2021-10-07

International audience. To detect cardiovascular diseases (CVD), electrocardiogram (ECG) of a patient must be recorded and analyzed for a long period. For an effective diagnosis, the ECG recording system must automa...

Event-driven ECG classification using an open-source, LC-ADC based non-uniformly sampled dataset | Saeed, M.

Event-driven ECG classification using an open-source, LC-ADC based non-unif...

Archive ouverte: Communication dans un congrès

Saeed, M. | 2021-05-22

The open-source event-driven ECG dataset is available at https://github.com/jedaiproject/Open-Source-Event-Driven-ECG-Dataset. International audience. In this article, non-uniformly sampled electrocardiogram (ECG) s...

Evaluation of Level-Crossing ADCs for Event-Driven ECG Classification | Saeed, Maryam

Evaluation of Level-Crossing ADCs for Event-Driven ECG Classification

Archive ouverte: Article de revue

Saeed, Maryam | 2021-12

International audience. In this paper, a new methodology for choosing design parameters of level-crossing analog-to-digital converters (LC-ADCs) is presented that improves sampling accuracy and reduces the data stre...

Event-Driven ECG Classification using Functional Approximation and Chebyshev Polynomials | Saeed, Maryam

Event-Driven ECG Classification using Functional Approximation and Chebyshe...

Archive ouverte: Communication dans un congrès

Saeed, Maryam | 2022-10-13

Level-crossing ADCs reduce the size of data streams in wearable devices. However, in the context of electrocardiogram (ECG) signals, such an event-driven data source results in a variable length two-dimensional (time-amplitude tup...

Signals to Spikes for Neuromorphic Regulated Reservoir Computing and EMG Hand Gesture Recognition | Garg, N.

Signals to Spikes for Neuromorphic Regulated Reservoir Computing and EMG Ha...

Archive ouverte: Communication dans un congrès

Garg, N. | 2021-07-27

International audience. Surface electromyogram (sEMG) signals result from muscle movement and hence they are an ideal candidate for benchmarking event-driven sensing and computing. We propose a simple yet novel appr...

Chargement des enrichissements...