Saba Kharabadze

This proposal addresses the Radar Challenge on robust heartbeat monitoring in the presence of random body motion (RBM). Our approach improves the estimation of heartbeat and its variability by combining conventional radar signal processing techniques with data-driven machine learning methods. We construct a multidimensional time-series representation from the stabilized chest signal, which serves as an input to the Transformer model. In addition, we propose a novel data augmentation strategy, where RBMs are modeled and simulated with stochastic processes. This increases the diversity of the training data and helps the model adapt to uncontrolled real-world conditions. The main innovations compared with the existing literature are: (i) the physics-guided design of a meaningful time-series input for the Transformer, and (ii) a stochastic augmentation method for synthetic RBM signals. Together, these strategies aim to achieve robust and reliable radar-based heartbeat monitoring in dynamic scenarios.

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 an additional stable Li3Sn phase with a large BCC-based hR48 structure and a possible high-T LiSn4 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, low-symmetry 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.

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.