AI Article Synopsis

  • Sleep posture significantly influences obstructive sleep apnea (OSA) severity; recognizing sleep positions can enhance OSA assessment.
  • Current systems for monitoring sleep postures, like contact-based and camera-based methods, have practical challenges, but radar technology offers a promising non-intrusive alternative.
  • This study tested various radar configurations and machine learning models to develop an effective sleep posture recognition system, achieving the best results with the Swin Transformer and side + head radar setup.

Article Abstract

Sleep posture has a crucial impact on the incidence and severity of obstructive sleep apnea (OSA). Therefore, the surveillance and recognition of sleep postures could facilitate the assessment of OSA. The existing contact-based systems might interfere with sleeping, while camera-based systems introduce privacy concerns. Radar-based systems might overcome these challenges, especially when individuals are covered with blankets. The aim of this research is to develop a nonobstructive multiple ultra-wideband radar sleep posture recognition system based on machine learning models. We evaluated three single-radar configurations (top, side, and head), three dual-radar configurations (top + side, top + head, and side + head), and one tri-radar configuration (top + side + head), in addition to machine learning models, including CNN-based networks (ResNet50, DenseNet121, and EfficientNetV2) and vision transformer-based networks (traditional vision transformer and Swin Transformer V2). Thirty participants ( = 30) were invited to perform four recumbent postures (supine, left side-lying, right side-lying, and prone). Data from eighteen participants were randomly chosen for model training, another six participants' data ( = 6) for model validation, and the remaining six participants' data ( = 6) for model testing. The Swin Transformer with side and head radar configuration achieved the highest prediction accuracy (0.808). Future research may consider the application of the synthetic aperture radar technique.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10006965PMC
http://dx.doi.org/10.3390/s23052475DOI Listing

Publication Analysis

Top Keywords

side head
16
sleep posture
12
top side
12
posture recognition
8
machine learning
8
learning models
8
configurations top
8
swin transformer
8
participants' data
8
data model
8

Similar Publications

Purpose: This study explored the clinical characteristics of patients with tinnitus who responded to sound therapy and established a predictive model to evaluate the effectiveness of this therapy according to the clinical characteristics.

Methods: A retrospective analysis was performed on 991 subjective tinnitus patients who received compound sound therapy in the Department of Otolaryngology of the local hospital from November 2019 to January 2022.

Results: We found that tinnitus patients with different therapeutic effects had significant differences in the tinnitus side ( = 0.

View Article and Find Full Text PDF

We observed a novel, nocturnal cleaning interaction between a cleaner shrimp (Genus ) and the giant moray eel () on a lagoonal patch reef in Moorea, French Polynesia. Over the course of an 85-min foraging bout (recorded on video by a snorkeler), we observed three separate, stereotyped cleaning interactions between and a cleaner shrimp in the genus Urocaridella (which surveys of Moorea biodiversity previously visually identified as ). During these interactions, the shrimp would slowly crawl along one of the eel's flanks towards its head, enter its mouth, emerge on the other side of its head, then crawl back towards the reef along the eel's opposite flank, often causing it to jolt in response.

View Article and Find Full Text PDF

Melanoma, a malignant skin tumor, presents significant treatment challenges, particularly in unresectable and metastatic cases. While immune checkpoint inhibitors (ICIs) targeting PD-1/PD-L1 have brought new hope, their efficacy is limited by low response rates and significant immune-mediated adverse events (irAEs). Through multi-omics data analysis, it is discovered that the spatial co-localization of CD73 and PD-L1 in melanoma correlates with improved progression-free survival (PFS), suggesting a synergistic potential of their inhibitors.

View Article and Find Full Text PDF

Diagnostic efficacy of body roll test for lateral canal BPPV: A randomized controlled study.

Clin Exp Otorhinolaryngol

December 2024

Department of Otorhinolaryngology-Head and Neck Surgery, Incheon St. Mary's Hospital, College of medicine, The Catholic University of Korea, Seoul, Republic of Korea.

Background: Lateral semicircular canal BPPV (LC-BPPV) is diagnosed by the head roll test (HRT), in which the head is rotated to move particles in the lateral canal, causing nystagmus. The body roll test (BRT) is performed in a rolling position with the body and head together, which has the advantage of safely rotating the head at the correct angle in both directions. This study aims to assess the diagnostic utility of the body roll test (BRT).

View Article and Find Full Text PDF

Purpose: This study analyzes temporal bone thickness in pediatric craniofacial anomalies patients to determine the optimal age for preoperative high-resolution computed tomography (HRCT) and enhance surgical planning of bone conduction hearing implants.

Methods: A retrospective examination of 370 temporal bone HRCT scans from 158 pediatric patients with craniofacial anomalies was conducted. Statistical analysis included descriptive statistics and correlation between age and skull thickness.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!

A PHP Error was encountered

Severity: Notice

Message: fwrite(): Write of 34 bytes failed with errno=28 No space left on device

Filename: drivers/Session_files_driver.php

Line Number: 272

Backtrace:

A PHP Error was encountered

Severity: Warning

Message: session_write_close(): Failed to write session data using user defined save handler. (session.save_path: /var/lib/php/sessions)

Filename: Unknown

Line Number: 0

Backtrace: