Machine Learning in RADAR-Based Physiological Signals Sensing: A Scoping Review of the Models, Datasets, and Metrics

In the field of physiological signals monitoring and its applications, non-contact technology is often proposed as a possible alternative to traditional contact devices. The ability to extract information about a patient’s health status in an unobtrusive way, without stressing the subject and without the need of qualified personnel, fuels research in this growing field. Among the various methodologies, RADAR-based non-contact technology is gaining great interest. This scoping review aims to summarize the main research lines concerning RADAR-based physiological sensing and machine learning applications reporting recent trends, issues and gaps with the scientific literature, best methodological practices, employed standards to be followed, challenges, and future directions. After a systematic search and screening, two hundred and seven papers were collected following the guidelines of PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses). The included records covered two macro-areas being regression of physiological signals or physiological features (n=77 papers) and the other a cluster of papers regarding the processing of RADAR-based physiological signals and features; the latter cluster concerns four fields of interest, being RADAR-based diagnosis (n=77), RADAR-based human behaviour monitoring (n=25), RADAR-based biometric authentication (n=19) and RADAR-based affective computing (n=9). Papers collected under the diagnosis category were further divided, on the basis of their aims: in breath pattern classification (n=41), infection detection (n=10), sleep stage classification (n=9), heart disease detection (n=9) and quality detection (n=8). Papers collected under the human behaviour monitoring were further divided based on their aims: fatigue detection (n=9), human detection (n=7), human localisation (n=4), human orientation (n=2), and activities classification (n=3).