Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Improved estimators for fractional Brownian motion via the expectation-maximization algorithm.

Russell Fischer1, Metin Akay

  • 1Thayer School of Engineering, Dartmouth College, Hanover, NH 03755, USA.

Medical Engineering & Physics
|March 14, 2002
PubMed
Summary

This study introduces a new Expectation-Maximization (EM) algorithm to estimate the Hurst exponent (H) in noisy Fractional Brownian Motion (FBM) data. The new method offers more accurate H estimations compared to existing techniques.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

MicroRNA-873 Suppresses Viability and Invasion of Colorectal Cancer Through KRAS/MAPK Signaling and Sensitizes Tumor Spheroids to 5-Fluorouracil in a 3D Microwell Model.

IEEE open journal of engineering in medicine and biology·2026
Same author

Tumor-Suppressive microRNA Therapy Inhibits Growth of Glioblastoma Multiforme Xenografts.

Cancers·2026
Same author

AI-Generated Motifs Distinguish Altered Spatiotemporal Pain Response in the VTA of Mice With Chronic Pain.

IEEE journal of biomedical and health informatics·2026
Same author

AI-Based Detection of Coronary Artery Occlusion Using Acoustic Biomarkers Before and After Stent Placement.

IEEE open journal of engineering in medicine and biology·2025
Same author

Non-Invasive Measurement of Elasticity in Glioblastoma Multiforme Validates Decreased TMZ Sensitivity in Astrocyte Co-Culture.

IEEE open journal of engineering in medicine and biology·2025
Same author

AI-Based Localized Latent Neural Representations of Acute and Chronic Pain in Rats.

IEEE journal of biomedical and health informatics·2025

Area of Science:

  • Signal processing
  • Statistical modeling
  • Time series analysis

Background:

  • Fractional Brownian motion (FBM) models phenomena with long-term dependencies and 1/f noise.
  • The Hurst exponent (H) quantifies FBM complexity, crucial for fields like image processing and heart rate variability (HRV).
  • Accurate estimation of H is vital for analyzing complex systems.

Purpose of the Study:

  • To develop and evaluate a novel 1D Expectation-Maximization (EM) algorithm for estimating the Hurst exponent (H) in signals composed of FBM and additive white noise.
  • To compare the performance of the new EM-based estimator against established methods like Maximum Likelihood Estimation (MLE) and Detrended Fluctuation Analysis (DFA).

Main Methods:

  • Development of a 1D estimator based on the Expectation-Maximization (EM) algorithm.

Related Experiment Videos

  • Application of the estimator to simulated noisy Fractional Brownian Motion (FBM) data.
  • Comparative performance analysis against MLE for FBM and DFA.

    • Main Results:

    • The developed EM estimator demonstrated superior accuracy in estimating the Hurst exponent (H) for noisy FBM data.
    • The EM estimator outperformed both the Maximum Likelihood Estimator (MLE) for FBM and Detrended Fluctuation Analysis (DFA).

    Conclusions:

    • The EM algorithm provides a more accurate method for Hurst exponent estimation in FBM signals corrupted by noise.
    • This advancement has significant implications for fields relying on accurate analysis of complex time series data, such as HRV and image processing.