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

Search research articles

Related Experiment Video

Updated: May 28, 2026

Utilizing vmTracking to Improve the Accuracy of Multi-Animal Pose Estimation in Rodent Social Behavior Studies

Utilizing vmTracking to Improve the Accuracy of Multi-Animal Pose Estimation in Rodent Social Behavior Studies

Published on: November 7, 2025

Virtual Mice, Real Errors: A Sensor-Aware Generative Framework for In Silico Ethology.

Reza Sayfoori¹, Goli Vaisi¹, Hung Cao^1,2,3

¹Department of Electrical Engineering and Computer Science, University of California, Irvine, Irvine, CA 92697, USA.

Sensors (Basel, Switzerland)

|May 27, 2026

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

Intravascular sensors to assess unstable plaques and their compositions: a review.

Progress in biomedical engineering (Bristol, England)·2026

Same author

Polarization Conforms Performance Variability in Amorphous Electrodeposited Iridium Oxide pH Sensors: A Thorough Surface Chemistry Investigation.

Sensors (Basel, Switzerland)·2024

Same author

Consecutive treatments of methamphetamine promote the development of cardiac pathological symptoms in zebrafish.

PloS one·2023

Same author

Investigation of EEG-Based Biometric Identification Using State-of-the-Art Neural Architectures on a Real-Time Raspberry Pi-Based System.

Sensors (Basel, Switzerland)·2022

Same author

Towards Multiplexed and Multimodal Biosensor Platforms in Real-Time Monitoring of Metabolic Disorders.

Sensors (Basel, Switzerland)·2022

Same author

Fetal Electrocardiogram Extraction from the Mother's Abdominal Signal Using the Ensemble Kalman Filter.

Sensors (Basel, Switzerland)·2022

We developed a sensor-aware generative framework to create realistic animal trajectories, overcoming limitations of traditional methods. This approach improves robustness in computational ethology tasks, enhancing data analysis for behavioral studies.

Area of Science:

Computational Ethology
Animal Behavior Analysis
Robotics and Sensor Systems

Background:

Long-duration animal trajectory analysis is crucial for computational ethology.
Current methods for generating large animal cohorts are costly and time-consuming.
Animal-use considerations also limit large-scale trajectory data acquisition.

Purpose of the Study:

To present a novel sensor-aware generative framework for synthesizing behaviorally plausible animal trajectories.
To separate latent behavioral dynamics from sensor-induced distortions.
To evaluate the framework's robustness and realism in modeling animal movement.

Main Methods:

A semi-Markov ethology model combined with occupancy calibration and state-conditioned kinematic generation.

Keywords:

computational ethology digital twin domain shift generative modeling line-of-sight (LoS)non-line-of-sight (NLoS)semi-Markov model sensor-aware modeling trajectory generation ultra-wideband (UWB)

More Related Videos

Behavioral Training Procedures for Head-fixed Virtual Reality in Mice

Behavioral Training Procedures for Head-fixed Virtual Reality in Mice

Published on: September 6, 2024

Behavioral Phenotyping of Murine Disease Models with the Integrated Behavioral Station (INBEST)

Behavioral Phenotyping of Murine Disease Models with the Integrated Behavioral Station (INBEST)

Published on: April 23, 2015

Related Experiment Videos

Last Updated: May 28, 2026

Utilizing vmTracking to Improve the Accuracy of Multi-Animal Pose Estimation in Rodent Social Behavior Studies

Utilizing vmTracking to Improve the Accuracy of Multi-Animal Pose Estimation in Rodent Social Behavior Studies

Published on: November 7, 2025

Behavioral Training Procedures for Head-fixed Virtual Reality in Mice

Behavioral Training Procedures for Head-fixed Virtual Reality in Mice

Published on: September 6, 2024

Behavioral Phenotyping of Murine Disease Models with the Integrated Behavioral Station (INBEST)

Behavioral Phenotyping of Murine Disease Models with the Integrated Behavioral Station (INBEST)

Published on: April 23, 2015

Incorporation of a regime-dependent Ultra-Wideband (UWB) observation channel modeling Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) conditions.

Evaluation using state occupancy, kinematic divergence, residual agreement, and mean-squared displacement across four UWB sessions.

Main Results:

The sensor-aware framework successfully synthesized plausible trajectories while reproducing observation distortions.
Sensor-aware conditioning significantly improved robustness in trajectory classification under LoS/NLoS domain shifts (AUC = 0.995).
Condition-agnostic baselines showed performance decline (AUC = 0.974 and 0.901).

Conclusions:

Sensor-aware in silico ethology is feasible as a proof-of-concept framework.
The framework enables controlled robustness studies and algorithm evaluation under realistic sensor distortions.
Future work requires validation on larger datasets for applications in synthetic cohort generation and disease modeling.