Seyedeh Fatemeh Mirhosseini

Seyedeh Fatemeh Mirhosseini

Auto-generated profile, based on publicly available information

Seyedeh Fatemeh Mirhosseini

SnT, Interdisciplinary Center for Security, Reliability and Trust, University of Luxembourg, Luxembourg, Luxembourg

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 November 2025 in IEEE Transactions on Radar Systems
Verified
Journal Article
Open access
SMSeyedeh Fatemeh Mirhosseini
Seyedeh Fatemeh Mirhosseini
MAMohammad Alaee-Kerahroodi
Mohammad Alaee-Kerahroodi
AOAndreas Olk
Andreas Olk
USUdo Schroeder
Udo Schroeder
BRBhavani Shankar Mysore R
Bhavani Shankar Mysore R
In-car vital signs monitoring using millimeter-wave (mmWave) radar sensors has attracted growing interest due to its non-intrusive, real-time, and privacy-preserving nature. Leveraging the high-resolution capabilities of mmWave radar technology, this paper proposes non-contact detection of human presence and measurement of vital signs such as respiration and heartbeat within a vehicle cabin. A range of spectral analysis techniques—both parametric and nonparametric—are employed, including Fast Fourier Transform (FFT), Periodogram, Correlogram, ESPRIT (Estimation of signal parameters via rotational invariant techniques), MUSIC (Multiple Signal Classification), Nonlinear Least Squares (NLS), and the Iterative Adaptive Approach (IAA), to extract vital sign information with high precision. For real-time measurements, we utilize three radar platforms operating in the 60 GHz band: the BGT60LTR11AIP (Pulse-Doppler), the BGT60TR13C (SIMO), and the IWR6843ISK (MIMO). Experiments were conducted in diverse environments, including laboratory settings, on-road scenarios, and a custom test setup using a pump-embedded dummy to simulate infant vital signs. To distinguish living beings from inanimate objects, statistical features such as variance, entropy, and the Kolmogorov–Smirnov (KS) test are extracted and used as input to Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) classifiers. The proposed solution is low-cost, privacy-preserving, and robust against environmental interference, making it ideal for integration into next-generation intelligent transportation systems.