Sergiy Zhuk

Jonathan P. Epperlein, Sergiy Zhuk

With a video data source, such as multispectral video acquired during administration of fluorescent tracers, extraction of time-resolved data typically requires the compensation of motion. While this can be done manually, which is arduous, or using off-the-shelf object tracking software, which often yields unsatisfactory performance, we present an algorithm which is simple and performant. Most importantly, we provide an open-source implementation, with an easy-to-use interface for researchers not inclined to write their own code, as well as Python modules that can be used programmatically.

Jason Frank, Sergiy Zhuk

In this paper we propose a new sequential data assimilation method for non-linear ordinary differential equations with compact state space. The method is designed so that the Lyapunov exponents of the corresponding estimation error dynamics are negative, i.e. the estimation error decays exponentially fast. The latter is shown to be the case for generic regular flow maps if and only if the observation matrix H satisfies detectability conditions: the rank of H must be at least as great as the number of nonnegative Lyapunov exponents of the underlying attractor. Numerical experiments illustrate the exponential convergence of the method and the sharpness of the theory for the case of Lorenz96 and Burgers equations with incomplete and noisy observations.

Mykhaylo Zayats, Małgorzata J. Zimoń, Kyongmin Yeo et al.

We propose a new design of a neural network for solving a zero shot super resolution problem for turbulent flows. We embed Luenberger-type observer into the network's architecture to inform the network of the physics of the process, and to provide error correction and stabilization mechanisms. In addition, to compensate for decrease of observer's performance due to the presence of unknown destabilizing forcing, the network is designed to estimate the contribution of the unknown forcing implicitly from the data over the course of training. By running a set of numerical experiments, we demonstrate that the proposed network does recover unknown forcing from data and is capable of predicting turbulent flows in high resolution from low resolution noisy observations.

Tigran Tchrakian, Sergiy Zhuk

In this paper, we introduce a new, fast data assimilation algorithm for a 2D linear advection equation with divergence-free coefficients. We first apply the nodal discontinuous Galerkin (DG) method to discretize the advection equation, and then employ a set of interconnected minimax state estimators (filters) which run in parallel on spatial elements possessing observations. The filters are interconnected by means of numerical Lax-Friedrichs fluxes. Each filter is discretised in time by a symplectic Mobius time integrator which preserves all quadratic invariants of the estimation error dynamics. The cost of the proposed algorithm scales linearly with the number of elements. Examples are presented using both synthetic and real data. In the latter case, satellite images are assimilated into a 2D model representing the motion of clouds across the surface of the Earth.

Rodrigo Ordonez-Hurtado, Bo Wen, Nicholas Barra et al.

Driving is a daily routine for many individuals across the globe. This paper presents the configuration and methodologies used to transform a vehicle into a connected ecosystem capable of assessing driver physiology. We integrated an array of commercial sensors from the automotive and digital health sectors along with driver inputs from the vehicle itself. This amalgamation of sensors allows for meticulous recording of the external conditions and driving maneuvers. These data streams are processed to extract key parameters, providing insights into driver behavior in relation to their external environment and illuminating vital physiological responses. This innovative driver evaluation system holds the potential to amplify road safety. Moreover, when paired with data from conventional health settings, it may enhance early detection of health-related complications.

Sergiy Zhuk

This paper describes a minimax state estimation approach for linear Differential-Algebraic Equations (DAE) with uncertain parameters. The approach addresses continuous-time DAE with non-stationary rectangular matrices and uncertain bounded deterministic input. An observation's noise is supposed to be random with zero mean and unknown bounded correlation function. Main results are a Generalized Kalman Duality (GKD) principle and sub-optimal minimax state estimation algorithm. GKD is derived by means of Young-Fenhel duality theorem. GKD proves that the minimax estimate coincides with a solution to a Dual Control Problem (DCP) with DAE constraints. The latter is ill-posed and, therefore, the DCP is solved by means of Tikhonov regularization approach resulting a sub-optimal state estimation algorithm in the form of filter. We illustrate the approach by an synthetic example and we discuss connections with impulse-observability.

Tigran Tchrakian, Mykhaylo Zayats, Alessandra Pascale et al.

Spinal cord stimulation (SCS) is a therapeutic approach used for the management of chronic pain. It involves the delivery of electrical impulses to the spinal cord via an implanted device, which when given suitable stimulus parameters can mask or block pain signals. Selection of optimal stimulation parameters usually happens in the clinic under the care of a provider whereas at-home SCS optimization is managed by the patient. In this paper, we propose a recommender system for the management of pain in chronic pain patients undergoing SCS. In particular, we use a contextual multi-armed bandit (CMAB) approach to develop a system that recommends SCS settings to patients with the aim of improving their condition. These recommendations, sent directly to patients though a digital health ecosystem, combined with a patient monitoring system closes the therapeutic loop around a chronic pain patient over their entire patient journey. We evaluated the system in a cohort of SCS-implanted ENVISION study subjects (Clinicaltrials.gov ID: NCT03240588) using a combination of quality of life metrics and Patient States (PS), a novel measure of holistic outcomes. SCS recommendations provided statistically significant improvement in clinical outcomes (pain and/or QoL) in 85\% of all subjects (N=21). Among subjects in moderate PS (N=7) prior to receiving recommendations, 100\% showed statistically significant improvements and 5/7 had improved PS dwell time. This analysis suggests SCS patients may benefit from SCS recommendations, resulting in additional clinical improvement on top of benefits already received from SCS therapy.

Sergiy Zhuk

Author's Summary of the dissertation for the degree of the Candidate of Science (physics and mathematics). The aim of the dissertation is to develop a generalized Kalman Duality concept applicable for linear unbounded non-invertible operators and introduce the minimax state estimation theory and algorithms for linear differential-algebraic equations. In particular, the dissertation pursues the following goals: - develop generalized duality concept for the minimax state estimation theory for DAEs with unknown but bounded model error and random observation noise with unknown but bounded correlation operator; - derive the minimax state estimation theory for linear DAEs with unknown but bounded model error and random observation noise with unknown but bounded correlation operator; - describe how the DAE model propagates uncertain parameters; - estimate the worst-case error; - construct fast estimation algorithms in the form of filters; - develop a tool for model validation, that is to assess how good the model describes observed phenomena. The dissertation contains the following new results: - generalized version of the Kalman duality principle is proposed allowing to handle unbounded linear model operators with non-trivial null-space; - new definitions of the minimax estimates for DAEs based on the generalized Kalman duality principle are proposed; - theorems of existence for minimax estimates are proved; - new minimax state estimation algorithms (in the form of filter and in the variational form) for DAE are proposed.

Nicola Mariella, Albert Akhriev, Francesco Tacchino et al.

Optimal Transport (OT) has fueled machine learning (ML) across many domains. When paired data measurements $(\boldsymbolμ, \boldsymbolν)$ are coupled to covariates, a challenging conditional distribution learning setting arises. Existing approaches for learning a $\textit{global}$ transport map parameterized through a potentially unseen context utilize Neural OT and largely rely on Brenier's theorem. Here, we propose a first-of-its-kind quantum computing formulation for amortized optimization of contextualized transportation plans. We exploit a direct link between doubly stochastic matrices and unitary operators thus unravelling a natural connection between OT and quantum computation. We verify our method (QontOT) on synthetic and real data by predicting variations in cell type distributions conditioned on drug dosage. Importantly we conduct a 24-qubit hardware experiment on a task challenging for classical computers and report a performance that cannot be matched with our classical neural OT approach. In sum, this is a first step toward learning to predict contextualized transportation plans through quantum computing.

Gabriele Agliardi, Giorgio Cortiana, Anton Dekusar et al.

Fidelity quantum kernels have shown promise in classification tasks, particularly when a group structure in the data can be identified and exploited through a covariant feature map. In fact, there exist classification problems on which covariant kernels provide a provable advantage, thus establishing a separation between quantum and classical learners. However, their practical application poses two challenges: on one side, the group structure may be unknown and approximate in real-world data, and on the other side, scaling to the `utility' regime (above 100 qubits) is affected by exponential concentration. In this work, we address said challenges by applying fidelity kernels to real-world data with unknown structure, related to the scheduling of a fleet of electric vehicles, and to synthetic data generated from the union of subspaces, which is then close to many relevant real-world datasets. Furthermore, we propose a novel error mitigation strategy specifically tailored for fidelity kernels, called Bit Flip Tolerance (BFT), to alleviate the exponential concentration in our utility-scale experiments. Our multiclass classification reaches accuracies comparable to classical SVCs up to 156 qubits, thus constituting the largest experimental demonstration of quantum machine learning on IBM devices to date. For the real-world data experiments, the effect of the proposed BFT becomes manifest on 40+ qubits, where mitigated accuracies reach 80%, in line with classical, compared to 33% without BFT. Through the union-of-subspace synthetic dataset with 156 qubits, we demonstrate a mitigated accuracy of 80%, compared to 83% of classical models, and 37% of unmitigated quantum, using a test set of limited size.

Jonathan P. Epperlein, Roman Overko, Sergiy Zhuk et al.

Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL agent, in which case the problem can be modeled as a contextual multi-armed bandit and lightweight myopic algorithms can be employed. On the other hand, when the RL agent's actions affect the environment, the problem must be modeled as a Markov decision process and more complex RL algorithms are required which take the future effects of actions into account. Moreover, in practice, it is often unknown from the outset whether or not the agent's actions will impact the environment and it is therefore not possible to determine which RL algorithm is most fitting. In this work, we propose to avoid this difficult decision entirely and incorporate a choice mechanism into our RL framework. Rather than assuming a specific problem structure, we use a probabilistic structure estimation procedure based on a likelihood-ratio (LR) test to make a more informed selection of learning algorithm. We derive a sufficient condition under which myopic policies are optimal, present an LR test for this condition, and derive a bound on the regret of our framework. We provide examples of real-world scenarios where our framework is needed and provide extensive simulations to validate our approach.

Sergiy Zhuk, Jonathan P. Epperlein, Rahul Nair et al.

Intra-operative identification of malignant versus benign or healthy tissue is a major challenge in fluorescence guided cancer surgery. We propose a perfusion quantification method for computer-aided interpretation of subtle differences in dynamic perfusion patterns which can be used to distinguish between normal tissue and benign or malignant tumors intra-operatively in real-time by using multispectral endoscopic videos. The method exploits the fact that vasculature arising from cancer angiogenesis gives tumors differing perfusion patterns from the surrounding tissue, and defines a signature of tumor which could be used to differentiate tumors from normal tissues. Experimental evaluation of our method on a cohort of colorectal cancer surgery endoscopic videos suggests that the proposed tumor signature is able to successfully discriminate between healthy, cancerous and benign tissue with 95% accuracy.

Roman Overko, Rodrigo H. Ordonez-Hurtado, Sergiy Zhuk et al.

We introduce a permissioned distributed ledger technology (DLT) design for crowdsourced smart mobility applications. This architecture is based on a directed acyclic graph architecture (similar to the IOTA tangle) and uses both Proof-of-Work and Proof-of-Position mechanisms to provide protection against spam attacks and malevolent actors. In addition to enabling individuals to retain ownership of their data and to monetize it, the architecture also is suitable for distributed privacy-preserving machine learning algorithms, is lightweight, and can be implemented in simple internet-of-things (IoT) devices. To demonstrate its efficacy, we apply this framework to reinforcement learning settings where a third party is interested in acquiring information from agents. In particular, one may be interested in sampling an unknown vehicular traffic flow in a city, using a DLT-type architecture and without perturbing the density, with the idea of realizing a set of virtual tokens as surrogates of real vehicles to explore geographical areas of interest. These tokens, whose authenticated position determines write access to the ledger, are thus used to emulate the probing actions of commanded (real) vehicles on a given planned route by "jumping" from a passing-by vehicle to another to complete the planned trajectory. Consequently, the environment stays unaffected (i.e., the autonomy of participating vehicles is not influenced by the algorithm), regardless of the number of emitted tokens. The design of such a DLT architecture is presented, and numerical results from large-scale simulations are provided to validate the proposed approach.

Jonathan P. Epperlein, Julien Monteil, Mingming Liu et al.

We present here a general framework and a specific algorithm for predicting the destination, route, or more generally a pattern, of an ongoing journey, building on the recent work of [Y. Lassoued, J. Monteil, Y. Gu, G. Russo, R. Shorten, and M. Mevissen, "Hidden Markov model for route and destination prediction," in IEEE International Conference on Intelligent Transportation Systems, 2017]. In the presented framework, known journey patterns are modelled as stochastic processes, emitting the road segments visited during the journey, and the ongoing journey is predicted by updating the posterior probability of each journey pattern given the road segments visited so far. In this contribution, we use Markov chains as models for the journey patterns, and consider the prediction as final, once one of the posterior probabilities crosses a predefined threshold. Despite the simplicity of both, examples run on a synthetic dataset demonstrate high accuracy of the made predictions.

Sergiy Zhuk, Tigran Tchrakian, Albert Akhriev et al.

This paper describes a new algorithm for solar energy forecasting from a sequence of Cloud Optical Depth (COD) images. The algorithm is based on the following simple observation: the dynamics of clouds represented by COD images resembles the motion (transport) of a density in a fluid flow. This suggests that, to forecast the motion of COD images, it is sufficient to forecast the flow. The latter, in turn, can be accomplished by fitting a parametric model of the fluid flow to the COD images observed in the past. Namely, the learning phase of the algorithm is composed of the following steps: (i) given a sequence of COD images, the snapshots of the optical flow are estimated from two consecutive COD images; (ii) these snapshots are then assimilated into a Navier-Stokes Equation (NSE), i.e. an initial velocity field for NSE is selected so that the corresponding NSE' solution is as close as possible to the optical flow snapshots. The prediction phase consists of utilizing a linear transport equation, which describes the propagation of COD images in the fluid flow predicted by NSE, to estimate the future motion of the COD images. The algorithm has been tested on COD images provided by two geostationary operational environmental satellites from NOAA serving the west-hemisphere.