Individual Identification Using Radar-Measured Respiratory and Heartbeat Features

This study proposes a method for radar-based identification of individuals using a combination of their respiratory and heartbeat features. In the proposed method, the target individual's respiratory features are extracted using the modified raised-cosine-waveform model and their heartbeat features are extracted using the mel-frequency cepstral analysis technique. To identify a suitable combination of features and a classifier, we compare the performances of nine methods based on various combinations of three feature vectors with three classifiers. The accuracy of the proposed method in performing individual identification is evaluated using a 79-GHz millimeter-wave radar system with an antenna array in two experimental scenarios and we demonstrate the importance of use of the combination of the respiratory and heartbeat features in achieving accurate identification of individuals. The proposed method achieves accuracy of 96.33% when applied to a five-day dataset of six participants and 99.39% when applied to a public one-day dataset of thirty participants.

Accurate Radar-Based Heartbeat Measurement Using Higher Harmonic Components

This study proposes a radar-based heartbeat measurement method that uses the absolute value of the second derivative of the complex radar signal, rather than its phase, and the variational mode extraction method, which is a type of mode decomposition algorithm. We show that the proposed second-derivative-based approach can amplify the heartbeat component in radar signals effectively and also confirm that use of the variational mode extraction method represents an efficient way to emphasize the heartbeat component amplified via the second-derivative-based approach. We demonstrate estimation of the heart interbeat intervals using the proposed approach in combination with the topology method, which is an accurate interbeat interval estimation method. The performance of the proposed method is evaluated quantitatively using data obtained from eleven participants that were measured using a millimeter-wave radar system. When compared with conventional methods based on the phase of the complex radar signal, our proposed method can achieve higher accuracy when estimating the heart interbeat intervals; the correlation coefficient for the proposed method was increased by 0.20 and the root-mean-square error decreased by 23%.

Crystal-LSBO: Automated Design of De Novo Crystals with Latent Space Bayesian Optimization

Generative modeling of crystal structures is significantly challenged by the complexity of input data, which constrains the ability of these models to explore and discover novel crystals. This complexity often confines de novo design methodologies to merely small perturbations of known crystals and hampers the effective application of advanced optimization techniques. One such optimization technique, Latent Space Bayesian Optimization (LSBO) has demonstrated promising results in uncovering novel objects across various domains, especially when combined with Variational Autoencoders (VAEs). Recognizing LSBO's potential and the critical need for innovative crystal discovery, we introduce Crystal-LSBO, a de novo design framework for crystals specifically tailored to enhance explorability within LSBO frameworks. Crystal-LSBO employs multiple VAEs, each dedicated to a distinct aspect of crystal structure: lattice, coordinates, and chemical elements, orchestrated by an integrative model that synthesizes these components into a cohesive output. This setup not only streamlines the learning process but also produces explorable latent spaces thanks to the decreased complexity of the learning task for each model, enabling LSBO approaches to operate. Our study pioneers the use of LSBO for de novo crystal design, demonstrating its efficacy through optimization tasks focused mainly on formation energy values. Our results highlight the effectiveness of our methodology, offering a new perspective for de novo crystal discovery.

Complex Number Assignment in the Topology Method for Heartbeat Interval Estimation Using Millimeter-Wave Radar

The topology method is an algorithm for accurate estimation of instantaneous heartbeat intervals using millimeter-wave radar signals. In this model, feature points are extracted from the skin displacement waveforms generated by heartbeats and a complex number is assigned to each feature point. However, these numbers have been assigned empirically and without solid justification. This study used a simplified model of displacement waveforms to predict the optimal choice of the complex number assignments to feature points corresponding to inflection points, and the validity of these numbers was confirmed using analysis of a publicly available dataset.

Radar-Based Estimation of Human Body Orientation Using Respiratory Features and Hierarchical Regression Model

This study proposes an accurate method to estimate human body orientation using a millimeter-wave radar system. Body displacement is measured from the phase of the radar echo, which is analyzed to obtain features associated with the fundamental and higher-order harmonic components of the quasi-periodic respiratory motion. These features are used in body-orientation estimation invoking a novel hierarchical regression model in which a logistic regression model is adopted in the first step to determine whether the target person is facing forwards or backwards; a pair of ridge regression models are employed in the second step to estimate body-orientation angle. To evaluate the performance of the proposed method, respiratory motions of five participants were recorded using three millimeter-wave radar systems; cross-validation was also performed. The average error in estimating body orientation angle was 38.3$^\circ$ and 23.1$^\circ$ using respectively a conventional method with only the fundamental frequency component and our proposed method, indicating an improvement in accuracy by factor 1.7 when using the proposed method. In addition, the coefficient of correlation between the actual and estimated body-orientation angles using the conventional and proposed methods are 0.74 and 0.91, respectively. These results show that by combining the characteristic features of the fundamental and higher-order harmonics from the respiratory motion, the proposed method offers better accuracy.