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 Concept Videos

Newman Projections02:06

Newman Projections

23.2K
Different notations are used to represent the three-dimensional structure of molecules on two-dimensional surfaces. One of the most commonly used representations is the dash-wedge formula. The dashed wedges, solid wedges, and the plane lines indicate the groups situated behind the plane, coming out of the plane, and in the plane, respectively.
The organic molecules rotate across the single bonds leading to numerous temporary three-dimensional structures of varying energy known as...
23.2K

You might also read

Related Articles

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

Sort by
Same author

Allium polyrhizum Turcz. flavonoid extract improved the growth performance, meat quality, serum biochemical indices, and immune organ indices of broilers.

Poultry science·2025
Same author

Protein kinase D is essential for embryonic survival through functionally redundant subtypes.

Life sciences·2025
Same author

Fluorescence lifetime imaging microscopy approach reveals quantitative signatures for hepatocellular carcinoma diagnosis.

Frontiers in oncology·2025
Same author

Deletion of <i>Ptpmt1</i> by <i>αMHC-Cre</i> in Mice Results in Left Ventricular Non-Compaction.

Journal of developmental biology·2025
Same author

Machine learning identifies prominent risk factors for depressive symptoms among Chinese children and adolescents.

Journal of affective disorders·2025
Same author

S-COS-Se mitigates cadmium-induced oxidative stress, inflammation, and immunotoxicity by restoring immune balance and inhibiting mitochondria-pyroptosis crosstalk.

Ecotoxicology and environmental safety·2025

Related Experiment Video

Updated: Mar 11, 2026

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

843

High Accuracy Human Activity Recognition Based on Sparse Locality Preserving Projections.

Xiangbin Zhu1, Huiling Qiu1

  • 1College of Mathematics, Physics and Information Engineering, Zhejiang Normal University, Zhejiang, China.

Plos One
|November 29, 2016
PubMed
Summary

This study introduces a novel three-stage continuous hidden Markov model (TSCHMM) for human activity recognition (HAR). The method enhances classification accuracy by effectively utilizing sequential data characteristics and optimized feature selection.

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.7K
Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.3K

Related Experiment Videos

Last Updated: Mar 11, 2026

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

843
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.7K
Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.3K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Signal Processing

Background:

  • Human activity recognition (HAR) using sensory data is crucial for healthcare, intelligent environments, and cybersecurity.
  • Existing HAR methods often lack sufficient classification accuracy, particularly in sensitive applications like healthcare.
  • The sequential nature and complex feature relationships within time-series sensory data present challenges for accurate HAR.

Purpose of the Study:

  • To develop a novel human activity recognition method that fully leverages the intrinsic sequential characteristics of time-series sensory data.
  • To improve classification accuracy in HAR, addressing limitations of current approaches, especially for healthcare applications.
  • To introduce a multi-stage classification strategy that accounts for correlated feature relationships at different levels.

Main Methods:

  • Proposed a three-stage continuous hidden Markov model (TSCHMM) for human activity recognition, encompassing coarse, fine, and accurate classification stages.
  • Employed sparse locality preserving projections (SpLPP) for feature reduction, optimizing feature subsets for stationary activity data classification.
  • Utilized gyro-based features for accurate classification of moving activity data.

Main Results:

  • The SpLPP method extracted more discriminative features from sensor data compared to standard locality preserving projections.
  • The TSCHMM approach demonstrated significantly reduced feature usage while achieving substantial improvements in overall classification accuracy.
  • The proposed method effectively handles the sequential characteristics and feature correlations inherent in time-series sensory data.

Conclusions:

  • The three-stage continuous hidden Markov model (TSCHMM) offers a significant advancement in human activity recognition accuracy.
  • The integration of SpLPP for feature selection enhances the discriminative power of the HAR system.
  • This novel approach provides a more accurate and efficient solution for HAR, with strong implications for healthcare and other fields.