Jove
Visualize
Contact Us

Related Concept Videos

Constructing and Visualizing Models using Mime-based Machine-learning Framework06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

2.3K
Mime is a flexible computational framework to construct a machine learning-based integration model with elegant performance. Here, we provide a detailed step-by-step procedure for developing predictive models with high accuracy, leveraging complex datasets to identify critical genes associated with disease progression, patient outcomes, and therapeutic response.
2.3K
A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss07:12

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss

884
We present development of a gaze-contingent display framework designed for perceptual and oculomotor research simulating central vision loss. This framework is particularly adaptable for studying compensatory behavioral and oculomotor strategies in individuals experiencing both simulated and pathological central vision...
884
An Open-Source Framework for Mass Calculation of Antibody-Based Therapeutic Molecules04:24

An Open-Source Framework for Mass Calculation of Antibody-Based Therapeutic Molecules

2.3K
This article describes the use of a software application, mAbScale, for the calculation of masses for monoclonal antibody-based protein...
2.3K
PPE Use in Healthcare Settings II: Doffing01:10

PPE Use in Healthcare Settings II: Doffing

1.6K
The sequence of removing or doffing PPE starts with the gloves, as they are the most contaminated. Next is removal of the face shield or goggles, as they would interfere with removing other PPE. Then remove the gown, followed by the mask or respirator. Perform hand hygiene between steps if hands become contaminated and immediately after removing all PPE. Generally, the outside front and sleeves of the isolation gown, the goggles or the mask, the respirator, and the face shield are contaminated.
1.6K
Asthma Detection Research Based on Voice Signal Processing and Machine Learning04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

939
This study employed voice signal analysis and machine learning methods, utilizing MATLAB to extract distinctive voice features for non-invasive early detection of asthma. The Support Vector Machine (SVM) and Random Forest (RF) algorithms demonstrated comparable performance in terms of overall classification accuracy, although SVM may achieve a better balance between sensitivity and...
939
COVID-19 / Coronavirus Outbreak: Doffing Personal Protective Equipment When Exiting A Patient Room04:30

COVID-19 / Coronavirus Outbreak: Doffing Personal Protective Equipment When Exiting A Patient Room

9.3K
In pandemic times, medical staff is becoming a key resource in fighting the infection. To achieve the best medical care, relevant techniques and procedures have to be taught to medical staff to reduce the risk of infection. Doffing the contaminated personal protective gear after treating COVID-19 patients has a high risk of forming infective aerosols which could lead to an infection of the medical staff. In this video, the manner of doffing of personal protective gear to minimize the risk of...
9.3K

You might also read

Related Articles

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

Sort by
Same author

Big team science reveals promises and limitations of machine learning efforts to model physiological markers of affective experience.

Royal Society open science·2025
Same author

Deep Sensing for Compressive Video Acquisition.

Sensors (Basel, Switzerland)·2023
Same author

Identification of Language-Induced Mental Load from Eye Behaviors in Virtual Reality.

Sensors (Basel, Switzerland)·2023
Same author

A Study on the Influence of Sensors in Frequency and Time Domains on Context Recognition.

Sensors (Basel, Switzerland)·2023
Same author

Effects of AR-Based Home Appliance Agents on User's Perception and Maintenance Behavior.

Sensors (Basel, Switzerland)·2023
Same author

Surface Normals and Light Directions From Shading and Polarization.

IEEE transactions on pattern analysis and machine intelligence·2021
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 Experiment Video

Updated: Jan 20, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

2.3K

End-to-End Learning Framework for IMU-Based 6-DOF Odometry.

João Paulo Silva do Monte Lima1,2, Hideaki Uchiyama3, Rin-Ichiro Taniguchi4

  • 1Departamento de Computação, Universidade Federal Rural de Pernambuco, Recife 52171-900, Brazil. jpsml@cin.ufpe.br.

Sensors (Basel, Switzerland)
|September 5, 2019
PubMed
Summary

This study introduces a novel end-to-end learning framework for six degrees of freedom (6-DOF) odometry using only inertial data from low-cost Inertial Measurement Units (IMUs). The method achieves accurate 3D trajectory estimation by optimizing pose representation and loss functions.

Keywords:
6-DOFIMUneural networksodometry

More Related Videos

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

884
Author Spotlight: Advancing Biotherapeutic Mass Calculation by Introducing mAbScale, a Python-Based Desktop Application
04:24

Author Spotlight: Advancing Biotherapeutic Mass Calculation by Introducing mAbScale, a Python-Based Desktop Application

Published on: June 16, 2023

2.3K

Related Experiment Videos

Last Updated: Jan 20, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

2.3K
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

884
Author Spotlight: Advancing Biotherapeutic Mass Calculation by Introducing mAbScale, a Python-Based Desktop Application
04:24

Author Spotlight: Advancing Biotherapeutic Mass Calculation by Introducing mAbScale, a Python-Based Desktop Application

Published on: June 16, 2023

2.3K

Area of Science:

  • Robotics and Autonomous Systems
  • Sensor Fusion and State Estimation
  • Machine Learning for Navigation

Background:

  • Inertial Measurement Units (IMUs) are ubiquitous on mobile platforms, offering a low-cost solution for motion sensing.
  • Estimating 6-DOF (six degrees of freedom) odometry solely from inertial data is challenging due to sensor drift and noise.
  • Existing methods often require additional sensors or complex calibration procedures.

Purpose of the Study:

  • To develop an end-to-end learning framework for 6-DOF odometry using only low-cost IMU data.
  • To investigate optimal relative pose representations and loss functions for inertial odometry.
  • To integrate a multi-task learning framework for balancing multiple pose distance metrics.

Main Methods:

  • Utilized a neural network architecture combining convolutional layers and a stacked bidirectional Long Short-Term Memory (LSTM) network.
  • Explored two 6-DOF relative pose representations: spherical coordinate vector and translation vector with unit quaternion.
  • Designed a composite loss function incorporating Mean Squared Error (MSE), Translation Mean Absolute Error (TMAE), Quaternion Multiplicative Error (QME), and Quaternion Inner Product (QIP).

Main Results:

  • The combination of translation vector and unit quaternion for pose representation, along with TMAE and QME for the loss function, yielded the most accurate results.
  • The proposed framework demonstrated superior performance compared to state-of-the-art inertial odometry techniques in qualitative and quantitative evaluations.
  • The multi-task learning framework effectively balanced the weights of different pose distance metrics.

Conclusions:

  • An effective end-to-end learning framework for 6-DOF inertial odometry has been presented.
  • The optimal configuration involves specific pose representations and loss functions, significantly improving trajectory estimation accuracy.
  • This approach enables leveraging low-cost IMUs for robust 3D trajectory estimation in various mobile applications.