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

Learning recurrent behaviors from heterogeneous multivariate time-series.

Florence Duchêne1, Catherine Garbay, Vincent Rialle

  • 1Laboratory TIMC-IMAG, Institut d'Ingénierie de l'Information de Santé, Faculté de médecine de Grenoble, 38706 La Tronche Cedex, France. floduchene@yahoo.fr

Artificial Intelligence in Medicine
|August 29, 2006
PubMed
Summary
This summary is machine-generated.

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

A Smart Shoe Insole to Monitor Frail Older Adults' Walking Speed: Results of Two Evaluation Phases Completed in a Living Lab and Through a 12-Week Pilot Study.

JMIR mHealth and uHealth·2022
Same author

Special issue on technology and neuropsychological rehabilitation: Overview and reflections on ways to conduct future studies and support clinical practice.

Neuropsychological rehabilitation·2018
Same author

Preventing and managing indoor falls with home-based technologies in mild and moderate Alzheimer's disease patients: pilot study in a community dwelling.

Dementia and geriatric cognitive disorders·2013
Same author

Efficacy of simple home-based technologies combined with a monitoring assistive center in decreasing falls in a frail elderly population (results of the Esoppe study).

Archives of gerontology and geriatrics·2012
Same author

[Alzheimer's disease and geolocation: initial results of the Estima study].

Soins. Gerontologie·2012
Same author

Mass data exploration in oncology: an information synthesis approach.

Journal of biomedical informatics·2009
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026
Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026
See all related articles

This study introduces a novel method for mining heterogeneous multivariate time-series, enabling the learning of meaningful patterns for monitoring applications. Early results show promise in building behavioral profiles from sensor data.

Area of Science:

  • Data Science
  • Artificial Intelligence
  • Time-Series Analysis

Background:

  • Time-series mining is crucial for monitoring systems, requiring analysis of large datasets to identify usual patterns and detect deviations.
  • Complex monitoring tasks often involve studying multiple heterogeneous parameters over time.

Purpose of the Study:

  • To propose a novel method for mining heterogeneous multivariate time-series.
  • To enable the learning of meaningful patterns from complex, mixed time-series data.

Main Methods:

  • The approach handles mixed time-series data, including pattern and non-pattern elements.
  • It accommodates imprecise pattern matches, outliers, stretching, and global translations of pattern instances.

Main Results:

Related Experiment Videos

  • The method was tested on synthetic data for home monitoring and early real-world sequences.
  • Results demonstrate the potential for building individual behavioral profiles using sensor-recorded parameters.

Conclusions:

  • The proposed time-series mining method yields very promising results.
  • Parameter tuning for the method presents a notable challenge.