Γεώργιος Παπαδόπουλος

Dimitar Georgiev, Álvaro Fernández-Galiana, Simon Vilms Pedersen et al.

Raman spectroscopy is widely used across scientific domains to characterize the chemical composition of samples in a non-destructive, label-free manner. Many applications entail the unmixing of signals from mixtures of molecular species to identify the individual components present and their proportions, yet conventional methods for chemometrics often struggle with complex mixture scenarios encountered in practice. Here, we develop hyperspectral unmixing algorithms based on autoencoder neural networks, and we systematically validate them using both synthetic and experimental benchmark datasets created in-house. Our results demonstrate that unmixing autoencoders provide improved accuracy, robustness and efficiency compared to standard unmixing methods. We also showcase the applicability of autoencoders to complex biological settings by showing improved biochemical characterization of volumetric Raman imaging data from a monocytic cell.

Georgios Papadopoulos, Hanna Kurniawati, Nicholas M. Patrikalakis

Over the last 20 years significant effort has been dedicated to the development of sampling-based motion planning algorithms such as the Rapidly-exploring Random Trees (RRT) and its asymptotically optimal version (e.g. RRT*). However, asymptotic optimality for RRT* only holds for linear and fully actuated systems or for a small number of non-linear systems (e.g. Dubin's car) for which a steering function is available. The purpose of this paper is to show that asymptotically optimal motion planning for dynamical systems with differential constraints can be achieved without the use of a steering function. We develop a novel analysis on sampling-based planning algorithms that sample the control space. This analysis demonstrated that asymptotically optimal path planning for any Lipschitz continuous dynamical system can be achieved by sampling the control space directly. We also determine theoretical bounds on the convergence rates for this class of algorithms. As the number of iterations increases, the trajectory generated by these algorithms, approaches the optimal control trajectory, with probability one. Simulation results are promising.