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

Reinforcement

Reinforcement

Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:

Observational Learning

Observational Learning

Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...

Muscle Coordination and Action

Muscle Coordination and Action

Muscle coordination is a complex and finely tuned process essential for smooth and purposeful movements like flexion, extension, adduction, abduction, and rotation. The human body orchestrates the actions of various muscles working in concert, each with a specific role. Four functional types describe how muscles work together: agonist, antagonist, synergist, and fixator.
Agonists
Agonist muscles, often called prime movers, are the primary muscles responsible for producing a specific movement....

Fixed Action Patterns

Fixed Action Patterns

A fixed action pattern (FAP) is a specific, hard-wired sequence of behaviors that occurs in response to an external stimulus, called a sign stimulus. The behavior is “fixed” because it is essentially unchangeable—proceeding similarly across individuals of a species every time it occurs.

You might also read

Related Articles

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

Sort by

Same author

A framework for evaluating factual consistency in automated text summarization with large language models and prompting strategies.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Digital phenotyping using wearable-determined physical behaviours and machine learning to detect depression and anxiety symptoms in a general population.

Psychiatry research·2026

Same author

Timing of MVPA and psychosocial outcomes in adolescents with overweight/obesity.

International journal of clinical and health psychology : IJCHP·2026

Same author

Compositional Associations of 24-h Movement Behaviors With Depressive and Anxiety Symptoms in Middle-Aged Adults.

Depression and anxiety·2026

Same author

Frequency of prognostically important acute myeloid leukemia mutations in the Iranian population: A systematic review and meta-analysis.

Caspian journal of internal medicine·2026

Same author

Data-driven leisure-time physical activity trajectories of over 46 years and their associations with cognition in nonagenarians: a cohort study.

The journals of gerontology. Series B, Psychological sciences and social sciences·2026

Search research articles

Related Experiment Video

Updated: Jul 3, 2025

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

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

Published on: December 15, 2023

A novel physical activity recognition approach using deep ensemble optimized transformers and reinforcement learning.

Sajad Ahmadian¹, Mehrdad Rostami², Vahid Farrahi³

¹Faculty of Information Technology, Kermanshah University of Technology, Kermanshah, Iran.

Neural Networks : the Official Journal of the International Neural Network Society

|February 11, 2024

Summary

This study introduces an advanced deep learning ensemble method for accurate human physical activity recognition using heart rate, speed, and distance data. The novel approach optimizes hyperparameters and integrates model results for superior performance in healthcare and athletics.

Keywords:

Deep learning Optimization Physical activity Reinforcement learning Transformer

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

Movement Retraining using Real-time Feedback of Performance

Movement Retraining using Real-time Feedback of Performance

Published on: January 17, 2013

Related Experiment Videos

Last Updated: Jul 3, 2025

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

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

Published on: December 15, 2023

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

Movement Retraining using Real-time Feedback of Performance

Movement Retraining using Real-time Feedback of Performance

Published on: January 17, 2013

Area of Science:

* Computer Science
* Biomedical Engineering
* Data Science

Background:

* Human physical activity recognition is crucial for healthcare, human-computer interaction, lifestyle monitoring, and athletics.
* Deep learning models are widely used but require optimal hyperparameter tuning, which is often manual and time-consuming.
* Integrating diverse data sources and model outputs presents challenges in physical activity recognition systems.

Purpose of the Study:

* To propose a novel ensemble method for enhanced physical activity recognition.
* To automatically optimize deep learning model hyperparameters using a modified arithmetic optimization algorithm.
* To develop a reinforcement learning-based ensemble for integrating multi-modal time-series data (heart rate, speed, distance).

Main Methods:

* A deep transformer-based time-series classification model was developed.
* Hyperparameter optimization was performed using a modified arithmetic optimization algorithm.
* A reinforcement learning approach was employed for ensemble learning to integrate classification results.

Main Results:

* The proposed ensemble method demonstrated superior performance on a real-world dataset compared to state-of-the-art models.
* Significant improvements were observed across key metrics: accuracy (+3.44%), precision (+9.45%), recall (+5.43%), specificity (+2.54%), and F1-score (+7.53%).
* The method effectively integrates time-series data from heart rate, speed, and distance for robust activity recognition.

Conclusions:

* The novel ensemble method offers a promising and efficient solution for automated physical activity recognition.
* Automatic hyperparameter optimization and reinforcement learning-based integration enhance system performance and applicability.
* This approach has significant potential for applications in health monitoring, sports science, and human-computer interaction.