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

You might also read

Related Articles

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

Sort by
Same author

MH-1M: A 1.34 Million-Sample Multi-Feature Android Malware Dataset with Rich Metadata.

Scientific data·2025
Same author

Inferring ECG Waveforms from PPG Signals with a Modified U-Net Neural Network.

Sensors (Basel, Switzerland)·2024
Same author

Applying Self-Supervised Representation Learning for Emotion Recognition Using Physiological Signals.

Sensors (Basel, Switzerland)·2022
Same author

How Validation Methodology Influences Human Activity Recognition Mobile Systems.

Sensors (Basel, Switzerland)·2022
Same author

Estimating ecoacoustic activity in the Amazon rainforest through Information Theory quantifiers.

PloS one·2020
Same author

Human Activity Recognition Using Inertial Sensors in a Smartphone: An Overview.

Sensors (Basel, Switzerland)·2019

Related Experiment Video

Updated: Dec 25, 2025

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.2K

A Smartphone Lightweight Method for Human Activity Recognition Based on Information Theory.

Hendrio Bragança1, Juan G Colonna1, Wesllen Sousa Lima1

  • 1Instituto de Computação, Universidade Federal do Amazonas, Manaus CEP 69067-005, Brazil.

Sensors (Basel, Switzerland)
|April 2, 2020
PubMed
Summary
This summary is machine-generated.

This study introduces HAR-SR, a new method for smartphone-based Human Activity Recognition (HAR). HAR-SR uses information theory to efficiently classify activities with 93% accuracy, reducing computational costs.

Keywords:
discrete domainhuman activity recognitioninertial sensorsinformation theorysymbolic representationtime series classification

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.1K
Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification
07:47

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

11.7K

Related Experiment Videos

Last Updated: Dec 25, 2025

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.2K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.1K
Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification
07:47

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

11.7K

Area of Science:

  • Computer Science
  • Machine Learning
  • Signal Processing

Background:

  • Smartphones are ubiquitous tools for monitoring daily life and enabling Human Activity Recognition (HAR).
  • Existing HAR methods on smartphones often face computational challenges, limiting their practical implementation.
  • Machine learning techniques leverage embedded sensors for human behavior recognition.

Purpose of the Study:

  • To develop an efficient Human Activity Recognition (HAR) method for smartphones.
  • To reduce the computational cost of HAR models.
  • To introduce novel features for improved activity classification.

Main Methods:

  • Proposed a novel method named HAR-SR.
  • Utilized information theory quantifiers as features extracted from sensor data.
  • Developed simple activity classification models using these features.
  • Evaluated the method on three public databases: SHOAIB, UCI, and WISDM.

Main Results:

  • Achieved 93% accuracy in activity classification using a leave-one-subject-out (LOSO) cross-validation.
  • Demonstrated increased efficiency in terms of computational cost compared to existing methods.
  • Successfully applied information theory quantifiers for HAR feature extraction.

Conclusions:

  • HAR-SR offers an efficient and accurate solution for smartphone-based Human Activity Recognition (HAR).
  • The proposed method effectively balances accuracy and computational cost.
  • Information theory-based features show promise for developing lightweight HAR systems.