Chaos Theory and ARTFA: Emerging Tools for Interpreting ECG Signals to Diagnose Cardiac Arrhythmias

Gupta, Varun; Mittal, M.; Mittal, Vikas

doi:10.1007/s11277-021-08411-5

Cited by 62 publications

(14 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some examples are (a) COVASIM which includes country-specific information on age and population density that can capture diverse behaviors of people belonging to different age groups [ 40 ], (b) fear-based model, by Epstein et al, simulated the spread of fear and contagion in a coupled fear-contagion spread of the pandemic [ 41 ]. Data-driven artificial intelligence models: The construction of data-driven models using artificial intelligence and neural networks is widespread in medical image recognition and diagnosis [ 42 – 44 ]. These are used to find patterns or deviations in medical images and data that skip the naked eye [ 45 , 46 ]].…”

Section: Related Workmentioning

confidence: 99%

A multiscale modeling framework to study the interdependence of brain, behavior, and pandemic

2023

View full text Add to dashboard Cite

A major constraint of the behavioral epidemiological models is the assumption that human behavior is static; however, it is highly dynamic, especially in uncertain circumstances during a pandemic. To incorporate the dynamicity of human nature in the existing epidemiological models, we propose a population-wide multi-time-scale theoretical framework that assimilates neuronal plasticity as the basis of altering human emotions and behavior. For that, variable connection weights between different brain regions and their firing frequencies are coupled with a compartmental susceptible–infected–recovered model to incorporate the intrinsic dynamicity in the contact transmission rate ( ). As an illustration, a model of fear conditioning in conjunction with awareness campaigns is developed and simulated. Results indicate that in the presence of fear conditioning, there exists an optimum duration of daily broadcast time during which awareness campaigns are most effective in mitigating the pandemic. Further, global sensitivity analysis using the Morris method highlighted that the learning rate and firing frequency of the unconditioned circuit are crucial regulators in modulating the emergent pandemic waves. The present study makes a case for incorporating neuronal dynamics as a basis of behavioral immune response and has further implications in designing awareness campaigns.

show abstract

Section: Related Workmentioning

confidence: 99%

A multiscale modeling framework to study the interdependence of brain, behavior, and pandemic

2023

View full text Add to dashboard Cite

show abstract

“…A ''reconstruction'' is obtained via setting each v a to 1 with a probability once the binary states are given to the hidden units as in Eq. (20). Therefore, the weight change is determined in Eq.…”

Section: Restricted Boltzmann Machinementioning

confidence: 99%

“…The proposed HD prediction model was executed in Python, and their resultant outcomes were observed. Moreover, the performance of the adopted scheme was compared to the existing classifiers like NN [18], RF [19], SVM, and KNN [20], in terms of specific measures like Accuracy, Bookmakers Informedness, FDR, FNR, FOR, F-Measure, MCC, NPV, Precision, Recall, specificity, Sensitivity, and Threat score, respectively. The analysis was performed for each measure considering the reduced feature set to 15, 20, 25, and 30 via proposed multiple kernel-based PCA.…”

Section: Simulation Proceduresmentioning

confidence: 99%

Heart Disease Classification Using Multiple K-PCA and Hybrid Deep Learning Approach

Kusuma¹,

R²

2022

Computer Systems Science and Engineering

View full text Add to dashboard Cite

“…ii) Gupta et. al., use chaos analysis to identify the main components of ECG fluctuations which allows the monitoring of irregularities and heart disease with high accuracy [13] [14]. iii) Zhu, Q., et.…”

Section: A Backgroundmentioning

confidence: 99%

Time-Frequency High Resolution Using Chaos In Detection

Pancoatl-Bortolotti¹,

Enríquez-Caldera²,

Costa³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>A non-linear Liènard-type system based on trigono-metric functions is designed and used as a highly sensitive signal detector. Based on the intermittence mechanism presented in some chaotic systems, an adaptive detection array formed by five chaotic oscillators is designed, tuned, and tested. In the array, each individual oscillator identifies changes in frequency for non-stationary weak signals and, with the array working in an adaptative mode, gives an estimate of the timing at which intermittence occurred allowing the representation of a time-frequency spectrogram even when high-level noise is present. This work also shows that the trigonometric based system has an asymptotically stable limit cycle centered at the origin through two methods: first under the fixed-point analysis and later by the Melnikov method that uses a family of periodic orbits. Once the self-sustained oscillations are produced, the system is configured to drive itself into a saddle-node bifurcation through an iterative method for searching and tuning parameters which, in turn, assures the route to chaotic intermittence. Through this mechanism, the new system can be used as a non-stationary signal detector that also provides a high resolution time-frequency representation. The computer experiments showed that the adaptive array is perfectly compatible with other second-order non-linear oscillators configured in the chaotic intermittence regime such as Duffing, Van der Pol, and Van der Pol - Duffing, achieving high detection rates under noisy conditions. Moreover, when the new Liènard-type oscillators are incorporated into the adaptive array, the detection sensitivity overcomes the SNR threshold present in all oscillators mentioned above and allows for reaching and maintaining a relative error around 1% under severe noise conditions down to about -60 dB SNR.</p>

show abstract

Chaos Theory and ARTFA: Emerging Tools for Interpreting ECG Signals to Diagnose Cardiac Arrhythmias

Cited by 62 publications

References 72 publications

A multiscale modeling framework to study the interdependence of brain, behavior, and pandemic

A multiscale modeling framework to study the interdependence of brain, behavior, and pandemic

Heart Disease Classification Using Multiple K-PCA and Hybrid Deep Learning Approach

Time-Frequency High Resolution Using Chaos In Detection

Contact Info

Product

Resources

About