Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Multimodal healthcare system for human activity recognition using multiple features and advanced ensemble classifier.

Digital health·2026

Same author

Toward intelligent rehabilitation: Multimodal human pose modeling with parametric meshes and graph-based temporal reasoning.

Digital health·2026

Same author

Deep locomotion prediction learning over biosensors, ambient sensors, and computer vision.

PloS one·2026

Same author

Correction: Multi-modal remote sensory learning for multi-objects over autonomous devices.

Frontiers in bioengineering and biotechnology·2025

Same author

Deep multimodal biomechanical analysis for lower back pain rehabilitation to improve patients stability.

Frontiers in bioengineering and biotechnology·2025

Same author

UAV-based intelligent traffic surveillance using recurrent neural networks and Swin transformer for dynamic environments.

Frontiers in neurorobotics·2025

Search research articles

Related Experiment Video

Updated: Nov 27, 2025

Home-Based Monitor for Gait and Activity Analysis

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

Wearable Inertial Sensors for Daily Activity Analysis Based on Adam Optimization and the Maximum Entropy Markov

Sheikh Badar Ud Din Tahir¹, Ahmad Jalal¹, Kibum Kim²

¹Department of Computer Science, Air University, Islamabad 44000, Pakistan.

Entropy (Basel, Switzerland)

|December 8, 2020

Summary

This summary is machine-generated.

This study introduces an advanced human activity recognition model using wearable inertial sensors. The system achieves high accuracy in recognizing daily activities, enhancing elderly care and human-machine interaction.

Keywords:

Adam optimization accelerometer and gyroscope sensors inertial sensors maximum entropy Markov model multi-fused features

More Related Videos

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

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

Published on: December 11, 2015

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

Published on: April 21, 2017

Related Experiment Videos

Last Updated: Nov 27, 2025

Home-Based Monitor for Gait and Activity Analysis

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

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

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

Published on: December 11, 2015

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

Published on: April 21, 2017

Area of Science:

Wearable sensor technology
Human activity recognition
Biomedical engineering

Background:

Wearable sensors are increasingly vital in healthcare, particularly for elderly independent living and comfort.
Accurate human activity recognition is crucial for applications ranging from health monitoring to human-machine interfaces.

Purpose of the Study:

To develop and evaluate a novel human activity recognition model utilizing data from wearable inertial sensors.
To enhance the accuracy and robustness of activity recognition for improved healthcare and interactive systems.

Main Methods:

Signal processing of inertial data (gyroscopes, accelerometers) using Savitzky-Golay, median, and Hampel filters.
Extraction of a multifused feature model combining statistical, wavelet, and binary features.
Optimization of features using adaptive moment estimation (Adam) and AdaDelta, followed by classification with the maximum entropy Markov model (MEMM).

Main Results:

The proposed model achieved high recognition accuracies: 91.25% on USC-HAD, 93.66% on IMSB, and 90.91% on Mhealth datasets.
Performance surpassed existing state-of-the-art statistical methods in human activity recognition.
The 'leave-one-out' cross-validation scheme ensured robust evaluation.

Conclusions:

The developed human activity recognition model demonstrates superior performance and accuracy.
The system shows significant potential for applications in man-machine interfaces, including health, robotics, gaming, and surveillance.
Advancements in wearable sensor technology are key to enabling more sophisticated and reliable human activity recognition systems.