arXiv subjects

Saba Kharabadze

Publications and source records attributed to Saba Kharabadze.

5 recordsLinked to original sources

arXiv2026

Transformer-Based Heartbeat Monitoring with FMCW Radar Under Random Body Motion

Millimeter-wave Frequency Modulated Continuous Wave (FMCW) radar enables contactless cardiac monitoring, but heartbeat estimation becomes challenging when respiration and random body motion (RBM) distort the radar signal. In this paper, we propose a hybrid framework for 77 GHz FMCW radar that combines model-based signal processing with a Convolutional Neural Network (CNN)-Transformer network. The first block extracts chest displacement and constructs meaningful high-level motion features from raw radar data, while the second block reconstructs a photoplethysmography (PPG)-like signal from the extracted features. In this study, a synchronized PPG signal is used as the ground truth for heartbeat monitoring in supervised training. The method is evaluated following the IEEE AESS Radar Challenge Problem I protocol using the official datasets and figures of merit across three motion scenarios: stationary, deep breathing, and RBM. Results show that the proposed architecture reliably reconstructs the PPG signal in all scenarios, achieving high fidelity in controlled conditions and maintaining robust performance under motion. This enables reliable average heart rate (AHR) and heart rate variability (HRV) estimation even where benchmark methods fail, and leads to the highest total score among the compared approaches.

eess.SP↗

arXiv2023

Machine learning search for stable binary Sn alloys with Na, Ca, Cu, Pd, and Ag

We present our findings of a large-scale screening for new synthesizable materials in five M-Sn binaries, M = Na, Ca, Cu, Pd, and Ag. The focus on these systems was motivated by the known richness of M-Sn properties with potential applications in energy storage, electronics packaging, and superconductivity. For the systematic exploration of the large configuration space, we relied on our recently developed MAISE-NET framework that constructs accurate neural network interatomic potentials and utilizes them to accelerate ab initio global structure searches. The scan of over two million candidate phases at a fraction of the typical ab initio calculation cost has uncovered 29 possible intermetallics thermodynamically stable at different temperatures and pressures (1 bar and 20 GPa). Notable predictions of ambient-pressure materials include a simple hP6-NaSn$_2$ phase, fcc-based Pd-rich alloys, tI36-PdSn$_2$ with a new prototype, and several high-temperature Sn-rich ground states in the Na-Sn, Cu-Sn, and Ag-Sn systems. Our modeling work also involved ab initio (re)examination of previously observed M-Sn compounds that helped explain the entropy-driven stabilization of known Cu-Sn phases. The study demonstrates the benefits of guiding structure searches with machine learning potentials and significantly expands the number of predicted thermodynamically stable crystalline intermetallics achieved with this strategy so far.

cond-mat.mtrl-sci↗

arXiv2023

Thermodynamic stability of Li-B-C compounds from first principles

Prediction of high-$T_{\rm{c}}$ superconductivity in hole-doped Li$_x$BC two decades ago has brought about an extensive effort to synthesize new materials with honeycomb B-C layers, but the thermodynamic stability of Li-B-C compounds remains largely unexplored. In this study, we use density functional theory to characterize well-established and recently reported Li-B-C phases. Our calculation of the Li chemical potential in Li$_x$BC helps estimate the ($T$,$P$) conditions required for delithiation of the LiBC parent material, while examination of B-C phases helps rationalize the observation of metastable BC$_3$ polymorphs with honeycomb and diamond-like morphologies. At the same time, we demonstrate that recently reported BC$_3$, LiBC$_3$, and Li$_2$B$_2$C phases with new crystal structures are both dynamically and thermodynamically unstable. With a combination of evolutionary optimization and rational design, we identify considerably more natural and favorable Li$_2$B$_2$C configurations that, nevertheless, remain above the thermodynamic stability threshold.

cond-mat.mtrl-sci↗

arXiv2022

Prediction of stable Li-Sn compounds: boosting ab initio searches with neural network potentials

The Li-Sn binary system has been the focus of extensive research because it features Li-rich alloys with potential applications as battery anodes. Our present re-examination of the binary system with a combination of machine learning and ab initio methods has allowed us to screen a vast configuration space and uncover a number of overlooked thermodynamically stable alloys. At ambient pressure, our evolutionary searches identified a new stable Li$_3$Sn phase with a large BCC-based hR48 structure and a possible high-T LiSn$_4$ ground state. By building a simple model for the observed and predicted Li-Sn BCC alloys we constructed an even larger viable hR75 structure at an exotic 19:6 stoichiometry. At 20 GPa, new 11:2, 5:1, and 9:2 phases found with our global searches destabilize previously proposed phases with high Li content. The findings showcase the appreciable promise machine learning interatomic potentials hold for accelerating ab initio prediction of complex materials.

cond-mat.mtrl-sci↗

arXiv2020

MAISE: Construction of neural network interatomic models and evolutionary structure optimization

Module for ab initio structure evolution (MAISE) is an open-source package for materials modeling and prediction. The code's main feature is an automated generation of neural network (NN) interatomic potentials for use in global structure searches. The systematic construction of Behler-Parrinello-type NN models approximating ab initio energy and forces relies on two approaches introduced in our recent studies. An evolutionary sampling scheme for generating reference structures improves the NNs' mapping of regions visited in unconstrained searches, while a stratified training approach enables the creation of standardized NN models for multiple elements. A more flexible NN architecture proposed here expands the applicability of the stratified scheme for an arbitrary number of elements. The full workflow in the NN development is managed with a customizable 'MAISE-NET' wrapper written in Python. The global structure optimization capability in MAISE is based on an evolutionary algorithm applicable for nanoparticles, films, and bulk crystals. A multitribe extension of the algorithm allows for an efficient simultaneous optimization of nanoparticles in a given size range. Implemented structure analysis functions include fingerprinting with radial distribution functions and finding space groups with the SPGLIB tool. This work overviews MAISE's available features, constructed models, and confirmed predictions.

physics.comp-ph↗