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

State Space Representation01:27

State Space Representation

786
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
786

You might also read

Related Articles

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

Sort by
Same author

Sti1 participates in the dynamics of protein aggregation triggered by glucose signaling in <i>Saccharomyces cerevisiae</i>.

Acta biochimica et biophysica Sinica·2026
Same author

Cross-subject generalization for EEG decoding: a survey of deep learning methods.

Progress in biomedical engineering (Bristol, England)·2026
Same author

Lipid nanocomposites for precisely triggered Ttc3 gene silencing in pulmonary fibrosis treatment.

Journal of controlled release : official journal of the Controlled Release Society·2026
Same author

A novel nanotherapeutic strategy: rescuing nucleus pulposus cells from fatty acid metabolic disorder and pyroptosis through ACOT13 by Chinese herbal formula nanoparticles.

Journal of nanobiotechnology·2026
Same author

Machine learning driven semi-automated framework for yeast sporulation efficiency quantification using ilastik segmentation and Fiji nuclear enumeration.

Fungal genetics and biology : FG & B·2025
Same author

Cadmium accumulation and translocation in maize cultivars on contaminated soils in southern China.

BMC plant biology·2025
Same journal

From Verbal Reports to Personalized Activity Trackers: Understanding the Challenges of Ground Truth Data Collection with Older Adults in the Wild.

Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies·2026
Same journal

CRoP: Context-wise Robust Static Human-Sensing Personalization.

Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies·2026
Same journal

Engagements with Generative AI and Personal Health Informatics: Opportunities for Planning, Tracking, Reflecting, and Acting around Personal Health Data.

Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies·2026
Same journal

SleepNet: Attention-Enhanced Robust Sleep Prediction using Dynamic Social Networks.

Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies·2026
Same journal

Enabling Older Adults to Provide High-quality Activity Labels: Unpacking Accuracy, Precision, and Granularity in Activity Labeling.

Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies·2026
Same journal

The Physical Activity Assessment Using Wearable Sensors (PAAWS) Dataset: Labeled Laboratory and Free-living Accelerometer Data.

Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies·2026
See all related articles

Related Experiment Video

Updated: May 5, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.6K

Self-Supervised Representation Learning and Temporal-Spectral Feature Fusion for Bed Occupancy Detection.

Yingjian Song1, Zaid Farooq Pitafi1, Fei Dou1

  • 1The University of Georgia, USA, Athens, Georgia.

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
|March 17, 2025
PubMed
Summary
This summary is machine-generated.

SeismoDot enhances automated sleep monitoring by improving bed occupancy detection. This novel approach uses self-supervised learning and feature fusion, achieving high accuracy across diverse environments with limited data.

Keywords:
Bed OccupancySelf-Supervised LearningSpectrum-temporal feature fusion

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
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

2.5K

Related Experiment Videos

Last Updated: May 5, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.6K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
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

2.5K

Area of Science:

  • Biomedical Engineering
  • Machine Learning for Healthcare
  • Sleep Science

Background:

  • Accurate bed occupancy detection is crucial for automated sleep monitoring systems, forming the basis for sleep activity and vital sign inference.
  • Existing methods struggle with generalization in real-world settings due to reliance on single environments and manual thresholding, which is time-consuming and suboptimal.
  • Acquiring extensive labeled sensory data for training is costly and time-intensive, highlighting the need for models that generalize well with limited data.

Purpose of the Study:

  • To develop a robust bed occupancy detection model that generalizes across diverse environments using limited data.
  • To introduce SeismoDot, a novel system integrating self-supervised learning and spectral-temporal feature fusion.
  • To overcome the limitations of conventional methods in terms of data requirements and environmental adaptability.

Main Methods:

  • Developed SeismoDot, featuring a self-supervised learning module co-optimized with the primary task for task-relevant representation learning.
  • Integrated a spectral-temporal feature fusion module to simultaneously leverage temporal and spectral information, increasing feature diversity.
  • Employed a combined approach to expand the embedding space diversity in both temporal and spectral domains for enhanced generalizability.

Main Results:

  • SeismoDot achieved high accuracy (98.49%) and F1 scores (98.08%) across 13 diverse environments.
  • The model demonstrated strong performance with limited data, maintaining 97.01% accuracy and 96.54% F1 score when trained on only 20% of the data (4 days).
  • The results indicate exceptional generalizability across various environmental settings, even with significant data limitations.

Conclusions:

  • SeismoDot offers a significant advancement in bed occupancy detection for automated sleep monitoring.
  • The proposed self-supervised and feature fusion approach effectively addresses the challenges of real-world generalization and limited data.
  • This method provides a scalable and efficient solution for reliable sleep monitoring systems.