Researchers have developed new methods for assessing body composition using millimeter-wave (mmWave) radar scans, which can penetrate clothing and preserve privacy. One approach uses multi-task learning to predict visceral adipose tissue (VAT) and body fat percentage (BFP) from mmWave data, achieving an average absolute error of 1.0 L for VAT and 3.2% for BFP. Another method employs an optimization framework to reconstruct 3D human shape and extract anthropometric measurements by fitting a parametric body model directly to mmWave point clouds, offering a fast, contactless, and privacy-preserving alternative to traditional methods. AI
IMPACT This research demonstrates the potential for mmWave technology to enable frequent, non-intrusive body composition assessments, which could impact personalized medicine and risk stratification in clinical settings.
RANK_REASON The cluster contains two arXiv papers detailing novel research methodologies for body composition assessment using mmWave technology.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
