Classification of electrocardiogram signals with support vector machines and extreme learning machine

Karpagachelvi, S.; Arthanari, M.; Sivakumar, M.

doi:10.1007/s00521-011-0572-z

Cited by 72 publications

(29 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the output of the DMap is high-dimensional, we use the support vector machine (SVM), a multivariate classification tool 15 , to quantify the dynamics separation. The SVM is a supervised machine learning algorithm.…”

Section: Discussionmentioning

confidence: 99%

Novel Imaging Revealing Inner Dynamics for Cardiovascular Waveform Analysis via Unsupervised Manifold Learning

Wang

Huang

et al. 2020

Anesthesia &Amp; Analgesia

View full text Add to dashboard Cite

Background: Cardiovascular waveforms contain information for clinical diagnosis. By "learning" and organizing the subtle change of waveform morphology from large amounts of raw waveform data, unsupervised manifold learning helps delineate a high-dimensional structure and display it as a novel three-dimensional (3D) image. We hypothesize that the shape of this structure conveys clinically relevant inner dynamics information. Methods:To validate this hypothesis, we investigate the electrocardiography (ECG) waveform for ischemic heart disease and arterial blood pressure (ABP) waveform in dynamic vasoactive episodes. We model each beat or pulse to be a point lying on a manifold, like a surface, and use the diffusion map (DMap) to establish the relationship among those pulses. The output of the DMap is converted to a 3D image for visualization. For ECG datasets, first we analyzed the non-ST-elevation ECG waveform distribution from unstable angina to healthy control in the 3D image, and we investigated intraoperative ST-elevation ECG waveforms to show the dynamic ECG waveform changes. For ABP datasets, we analyzed waveforms collected under endotracheal intubation and administration of vasodilator. To quantify the dynamic separation, we applied the support vector machine (SVM) analysis and reported the total accuracy and macro F1 score. We further carried out the trajectory analysis and derived the moving direction of successive beats (or pulses) as vectors in the high-dimensional space.Results: For the non-ST-elevation ECG, a hierarchical tree structure comprising consecutive ECG waveforms spanning from unstable angina to healthy control is presented in the 3D image (accuracy = 97.6%, macro-F1=96.1%). The DMap helps quantify and visualize the evolving direction of intraoperative ST-elevation myocardial episode in a 1-hour period (accuracy=97.58%, macro-F1=96.06%). The ABP waveform analysis of Nicardipine administration shows inter-individual difference (accuracy=95.01%, macro-F1=96.9%) and their common directions from intra-individual moving trajectories. The dynamic change of the ABP waveform during endotracheal intubation shows a loop-like trajectory structure, which can be further divided using the manifold learning knowledge obtained from Nicardipine. Conclusions:The DMap and the generated 3D image of ECG or ABP waveforms provides clinically relevant inner dynamics information. It provides clues of acute coronary syndrome diagnosis, shows clinical course in myocardial ischemic episode and reveals underneath physiological mechanism under stress or vasodilators.Keywords: manifold learning, diffusion map, electrocardiography, myocardial ischemia, arterial 10,583 ECG beats, including clinical unstable angina (red), ischemic ECG pattern (green), and healthy control (blue). Video F3CCorresponding to Figure 3 panel C, it shows the 3D animation of 1-min ECG beats during the intra-operative ST-elevation event. Video F3DCorresponding to Figure 3 panel D, it shows the 3D animation of 4,299 consecutive ECG 31 beats from the IS...

show abstract

Section: Discussionmentioning

confidence: 99%

Novel Imaging Revealing Inner Dynamics for Cardiovascular Waveform Analysis via Unsupervised Manifold Learning

Wang

Huang

et al. 2020

Anesthesia &Amp; Analgesia

View full text Add to dashboard Cite

show abstract

“…SVM map is a given set of binary labelled of each training sample to a high dimensional feature space and separate the two classes of sample is available with a maximum margin of hyper-plane. SVM algorithm seeks to maximize the margin around a hyper-plane, which separates a positive class from a negative class as shown in equations (1), (2) and (3), [13].…”

Section: Support Vector Machines (Svms)mentioning

confidence: 99%

New Hybrid (SVMs -CSOA) Architecture for classifying Electrocardiograms Signals

Abed¹,

Alasad²

2015

ijarai

View full text Add to dashboard Cite

Abstract-a medical test that provides diagnostic relevant information of the heart activity is obtained by means of an ElectroCardioGram (ECG). Many heart diseases can be found by analyzing ECG because this method with moral performance is very helpful for shaping human heart status. Support Vector Machines (SVM) has been widely applied in classification. In this paper we present the SVM parameter optimization approach using novel metaheuristic for evolutionary optimization algorithms is Cat Swarm Optimization Algorithm (CSOA). The results obtained assess the feasibility of new hybrid (SVMs -CSOA) architecture and demonstrate an improvement in terms of accuracy.

show abstract

“…In a fuzzy inference system, basically there are three types of input space partitioning these are; grid partitioning, tree partitioning and scattering partitioning. As indicated by [22], [23] and [24], the grid-type partition which automatically generates rule is the default partitioning method in genfis1 command.…”

Section: ) Construction Of the Anfis Structurementioning

confidence: 99%

Adaptive neuro-fuzzy control of wet scrubbing process

Salami

Danzomo

Khan

2015

2015 10th Asian Control Conference (ASCC)

View full text Add to dashboard Cite

Thenon-linear characteristics of wet scrubbing process have led to the application of intelligent control technique to adequately deal with these complexities by manipulating the liquid droplet size for the effective control of particulate matter (PM) contaminants. This includes the use of adaptive neuro-fuzzy inference system (ANFIS) to design an intelligent controller based on direct inverse model control strategy using default input and output membership functions (gaussmf and linear) and different number of input membership functions. This is followed by training of the fuzzy inference system to obtain inverse model which was tested as the intelligent controller. The controller developed using two-input membership functions have successfully achieved the main target of setting the PM concentration (process output) below the set point which is the allowable World health organization (WHO) emission level for 20g/μm within a short settling time of 2s.

show abstract

Classification of electrocardiogram signals with support vector machines and extreme learning machine

Cited by 72 publications

References 17 publications

Novel Imaging Revealing Inner Dynamics for Cardiovascular Waveform Analysis via Unsupervised Manifold Learning

Novel Imaging Revealing Inner Dynamics for Cardiovascular Waveform Analysis via Unsupervised Manifold Learning

New Hybrid (SVMs -CSOA) Architecture for classifying Electrocardiograms Signals

Adaptive neuro-fuzzy control of wet scrubbing process

Contact Info

Product

Resources

About