arXiv subjects

Tales Imbiriba

Publications and source records attributed to Tales Imbiriba.

At least 19 recordsLinked to original sources

arXiv2026

Recursive Deep Inverse Reinforcement Learning

Inferring an adversary's goals from exhibited behavior is crucial for counterplanning and non-cooperative multi-agent systems in domains like cybersecurity, military, and strategy games. Deep Inverse Reinforcement Learning (IRL) methods based on maximum entropy principles show promise in recovering adversaries goals but are typically offline, require large batch sizes with gradient descent, and rely on first-order updates, limiting their applicability in real-time scenarios. We propose an online Recursive Deep Inverse Reinforcement Learning (RDIRL) approach to recover the cost function governing the adversary actions and goals. Specifically, we minimize an upper bound on the standard Guided Cost Learning (GCL) objective using sequential second-order Newton updates, akin to the Extended Kalman Filter (EKF), leading to a fast (in terms of convergence) learning algorithm. We demonstrate that RDIRL is able to recover cost and reward functions of expert agents in standard and adversarial benchmark tasks. Experiments on benchmark tasks show that our proposed approach outperforms several leading IRL algorithms.

cs.LG↗

arXiv2026

RTS Smoother-Guided Learning of Physics-Based Neural Differential Models

Ordinary differential equations (ODEs) are widely used to model dynamical systems in physics, biology, neuroscience, and physiology, but in many applications some equations of the dynamics are unknown and only a subset of the state variables are measured. We propose a hybrid neural--physics framework in which the known components of the ODE are kept explicit and the missing components are represented by a neural network. The proposed method consists of two stages where we alternate between state and parameter estimation and iterate until a predetermined criterion is met. Specifically, in the first step, we treat the model parameters as being known and we infer the latent states from the available measurements using a Rauch--Tung--Striebel (RTS) smoother. In the second stage, we treat the smoothed trajectories as being known and use them to estimate the neural networks' parameters through backpropagation. We evaluate the method on benchmark systems spanning linear, nonlinear, and stiff dynamics under partial state observation. Across these settings, the proposed method learns missing ODE components from incomplete measurements while exploiting and retaining interpretable mechanistic structure and improving latent-state reconstruction and long-horizon prediction.

cs.LG↗

arXiv2026

Temporal Point Process Modeling of Aggressive Behavior Onset in Psychiatric Inpatient Youths with Autism

Aggressive behavior, including aggression towards others and self-injury, occurs in up to 80% of children and adolescents with autism, making it a leading cause of behavioral health referrals and a major driver of healthcare costs. Predicting when autistic youth will exhibit aggression can be challenging due to their communication difficulties. Many are minimally verbal or have poor emotional insight. Recent advances in Machine Learning and wearable biosensing demonstrate the ability to predict aggression within a limited future window (typically one to three minutes) in autistic individuals. However, existing works don't estimate aggression onset probability or the expected number of aggression onsets over longer periods, nor do they provide interpretable insights into onset dynamics. To address these limitations, we apply Temporal Point Processes (TPPs) - particularly self-exciting Hawkes processes - to model the timing of aggressive behavior onsets in psychiatric inpatient autistic youth. We benchmark several TPP models by evaluating their goodness-of-fit and predictive metrics. Our results demonstrate that self-exciting TPPs more accurately captures the irregular and clustered nature of aggression onsets, especially compared to traditional Poisson models. These incipient findings suggest that TPPs can provide interpretable, probabilistic forecasts of aggression onset along a time continuum, supporting future clinical decision-making and preemptive intervention.

stat.AP↗

arXiv2025

SSplain: Sparse and Smooth Explainer for Retinopathy of Prematurity Classification

Neural networks are frequently used in medical diagnosis. However, due to their black-box nature, model explainers are used to help clinicians understand better and trust model outputs. This paper introduces an explainer method for classifying Retinopathy of Prematurity (ROP) from fundus images. Previous methods fail to generate explanations that preserve input image structures such as smoothness and sparsity. We introduce Sparse and Smooth Explainer (SSplain), a method that generates pixel-wise explanations while preserving image structures by enforcing smoothness and sparsity. This results in realistic explanations to enhance the understanding of the given black-box model. To achieve this goal, we define an optimization problem with combinatorial constraints and solve it using the Alternating Direction Method of Multipliers (ADMM). Experimental results show that SSplain outperforms commonly used explainers in terms of both post-hoc accuracy and smoothness analyses. Additionally, SSplain identifies features that are consistent with domain-understandable features that clinicians consider as discriminative factors for ROP. We also show SSplain's generalization by applying it to additional publicly available datasets. Code is available at https://github.com/neu-spiral/SSplain.

cs.CV↗

arXiv2025

Tubular Curvature Filter: Pointwise Curvature Calculation for Tubular Objects in Images

Purpose: Accurate estimation of blood vessel tortuosity from medical images is an extremely important and challenging task. It is particularly relevant in the context of retinopathy of prematurity (ROP), where the staging of disease severity and consequent therapeutic approaches are heavily informed by the presence and prominence of vessel tortuosity. Existing methods based on centerline or skeleton curvature fail to capture curvature gradients across a rotating tubular structure, thereby limiting their effectiveness in the case of ROP. Methods: This paper defines local tubular curvature and presents the Tubular Curvature Filter (TCF) method, which locally calculates the acceleration of curve bundles traversing a tubular object parallel to its centerline. This is achieved by examining the directional rate of change in the eigenvectors of the Hessian matrix of a tubular intensity function in space. TCF implicitly calculates the local tubular curvature without the need to explicitly segment or extracting the centerline of the tubular object. Results: Experimental results demonstrate that TCF provides accurate estimates of local curvature at any point inside tubular structures. Results on 2D and 3D images show that TCF discerns curvature differences between the inner and outer sides of curved tubular objects, while centerline-based approaches cannot. Conclusion: Our findings highlight that TCF's ability to discern between the inner and outer sides of curved tubular objects is particularly useful in medical fields that require vasculature curvature analysis from images, especially where vascular structures often have non-uniform diameters, such as in ROP.

eess.IV↗

arXiv2025

Trends and Challenges in Next-Generation GNSS Interference Management

The global navigation satellite system (GNSS) continues to evolve in order to meet the demands of emerging applications such as autonomous driving and smart environmental monitoring. However, these advancements are accompanied by a rise in interference threats, which can significantly compromise the reliability and safety of GNSS. Such interference problems are typically addressed through signal-processing techniques that rely on physics-based mathematical models. Unfortunately, solutions of this nature can often fail to fully capture the complex forms of interference. To address this, artificial intelligence (AI)-inspired solutions are expected to play a key role in future interference management solutions, thanks to their ability to exploit data in addition to physics-based models. This magazine paper discusses the main challenges and tasks required to secure GNSS and present a research vision on how AI can be leveraged towards achieving more robust GNSS-based positioning.

eess.SP↗

arXiv2025

Bayesian Jammer Localization with a Hybrid CNN and Path-Loss Mixture of Experts

Global Navigation Satellite System (GNSS) signals are vulnerable to jamming, particularly in urban areas where multipath and shadowing distort received power. Previous data-driven approaches achieved reasonable localization but poorly reconstructed the received signal strength (RSS) field due to limited spatial context. We propose a hybrid Bayesian mixture-of-experts framework that fuses a physical path-loss (PL) model and a convolutional neural network (CNN) through log-linear pooling. The PL expert ensures physical consistency, while the CNN leverages building-height maps to capture urban propagation effects. Bayesian inference with Laplace approximation provides posterior uncertainty over both the jammer position and RSS field. Experiments on urban ray-tracing data show that localization accuracy improves and uncertainty decreases with more training points, while uncertainty concentrates near the jammer and along urban canyons where propagation is most sensitive.

cs.LG↗

arXiv2025

Active Jammer Localization via Acquisition-Aware Path Planning

We propose an active jammer localization framework that combines Bayesian optimization with acquisition-aware path planning. Unlike passive crowdsourced methods, our approach adaptively guides a mobile agent to collect high-utility Received Signal Strength measurements while accounting for urban obstacles and mobility constraints. For this, we modified the A* algorithm, A-UCB*, by incorporating acquisition values into trajectory costs, leading to high-acquisition planned paths. Simulations on realistic urban scenarios show that the proposed method achieves accurate localization with fewer measurements compared to uninformed baselines, demonstrating consistent performance under different environments.

cs.LG↗

arXiv2025

Dependency-aware Maximum Likelihood Estimation for Active Learning

Active learning aims to efficiently build a labeled training set by strategically selecting samples to query labels from annotators. In this sequential process, each sample acquisition influences subsequent selections, causing dependencies among samples in the labeled set. However, these dependencies are overlooked during the model parameter estimation stage when updating the model using Maximum Likelihood Estimation (MLE), a conventional method that assumes independent and identically distributed (i.i.d.) data. We propose Dependency-aware MLE (DMLE), which corrects MLE within the active learning framework by addressing sample dependencies typically neglected due to the i.i.d. assumption, ensuring consistency with active learning principles in the model parameter estimation process. This improved method achieves superior performance across multiple benchmark datasets, reaching higher performance in earlier cycles compared to conventional MLE. Specifically, we observe average accuracy improvements of 6%, 8.6%, and 10.5% for k=1, k=5, and k=10 respectively, after collecting the first 100 samples, where entropy is the acquisition function and k is the query batch size acquired at every active learning cycle. Our implementation is publicly available at: https://github.com/neu-spiral/DMLEforAL

cs.LG↗

arXiv2025

Robust Recursive Fusion of Multiresolution Multispectral Images with Location-Aware Neural Networks

Multiresolution image fusion is a key problem for real-time satellite imaging and plays a central role in detecting and monitoring natural phenomena such as floods. It aims to solve the trade-off between temporal and spatial resolution in remote sensing instruments. Although several algorithms have been proposed for this problem, the presence of outliers such as clouds downgrades their performance. Moreover, strategies that integrate robustness, recursive operation and learned models are missing. In this paper, a robust recursive image fusion framework leveraging location-aware neural networks (NN) to model the image dynamics is proposed. Outliers are modeled by representing the probability of contamination of a given pixel and band. A NN model trained on a small dataset provides accurate predictions of the stochastic image time evolution, which improves both the accuracy and robustness of the method. A recursive solution is proposed to estimate the high-resolution images using a Bayesian variational inference framework. Experiments fusing images from the Landsat 8 and MODIS instruments show that the proposed approach is significantly more robust against cloud cover, without losing performance when no clouds are present.

eess.IV↗

arXiv2025

Hierarchical Temporal Point Process Modeling of Aggressive Behavior Onset in Psychiatric Inpatient Youth with Autism for Branching Factor Estimation

Aggressive behavior in autistic inpatient youth often arises in temporally clustered bursts complicating efforts to distinguish external triggers from internal escalation. The sample population branching factor-the expected number of new onsets triggered by a given event-is a key summary of self-excitation in behavior dynamics. Prior pooled models overestimate this quantity by ignoring patient-specific variability. We addressed this using a hierarchical Hawkes process with an exponential kernel and edge-effect correction allowing partial pooling across patients. This approach reduces bias from high-frequency individuals and stabilizes estimates for those with sparse data. Bayesian inference was performed using the No U-Turn Sampler with model evaluation via convergence diagnostics, power-scaling sensitivity analysis, and multiple Goodness-of-Fit (GOF) metrics: PSIS-LOO the Lewis test with Durbin's modification and residual analysis based on the Random Time Change Theorem (RTCT). The hierarchical model yielded a significantly lower and more precise branching factor estimate mean (0.742 +- 0.026) than the pooled model (0.899 +- 0.015) and narrower intervals than the unpooled model (0.717 +- 0.139). This led to a threefold smaller cascade of events per onset under the hierarchical model. Sensitivity analyses confirmed robustness to prior and likelihood perturbations while the unpooled model showed instability for sparse individuals. GOF measures consistently favored or on par to the hierarchical model. Hierarchical Hawkes modeling with edge-effect correction provides robust estimation of branching dynamics by capturing both within- and between-patient variability. This enables clearer separation of endogenous from exogenous events supports linkage to physiological signals and enhances early warning systems individualized treatment and resource allocation in inpatient care.

stat.AP↗

arXiv2025

Interpretable Augmented Physics-Based Model for Estimation and Tracking

State-space estimation and tracking rely on accurate dynamical models to perform well. However, obtaining an vaccurate dynamical model for complex scenarios or adapting to changes in the system poses challenges to the estimation process. Recently, augmented physics-based models (APBMs) appear as an appealing strategy to cope with these challenges where the composition of a small and adaptive neural network with known physics-based models (PBM) is learned on the fly following an augmented state-space estimation approach. A major issue when introducing data-driven components in such a scenario is the danger of compromising the meaning (or interpretability) of estimated states. In this work, we propose a novel constrained estimation strategy that constrains the APBM dynamics close to the PBM. The novel state-space constrained approach leads to more flexible ways to impose constraints than the traditional APBM approach. Our experiments with a radar-tracking scenario demonstrate different aspects of the proposed approach and the trade-offs inherent in the imposed constraints.

eess.SY↗

arXiv2025

Continuously Optimizing Radar Placement with Model Predictive Path Integrals

Continuously optimizing sensor placement is essential for precise target localization in various military and civilian applications. While information theory has shown promise in optimizing sensor placement, many studies oversimplify sensor measurement models or neglect dynamic constraints of mobile sensors. To address these challenges, we employ a range measurement model that incorporates radar parameters and radar-target distance, coupled with Model Predictive Path Integral (MPPI) control to manage complex environmental obstacles and dynamic constraints. We compare the proposed approach against stationary radars or simplified range measurement models based on the root mean squared error (RMSE) of the Cubature Kalman Filter (CKF) estimator for the targets' state. Additionally, we visualize the evolving geometry of radars and targets over time, highlighting areas of highest measurement information gain, demonstrating the strengths of the approach. The proposed strategy outperforms stationary radars and simplified range measurement models in target localization, achieving a 38-74% reduction in mean RMSE and a 33-79% reduction in the upper tail of the 90% Highest Density Interval (HDI) over 500 Monte Carl (MC) trials across all time steps. Code will be made publicly available upon acceptance.

stat.AP↗

arXiv2025

AI-Aided Kalman Filters

The Kalman filter (KF) and its variants are among the most celebrated algorithms in signal processing. These methods are used for state estimation of dynamic systems by relying on mathematical representations in the form of simple state-space (SS) models, which may be crude and inaccurate descriptions of the underlying dynamics. Emerging data-centric artificial intelligence (AI) techniques tackle these tasks using deep neural networks (DNNs), which are model-agnostic. Recent developments illustrate the possibility of fusing DNNs with classic Kalman-type filtering, obtaining systems that learn to track in partially known dynamics. This article provides a tutorial-style overview of design approaches for incorporating AI in aiding KF-type algorithms. We review both generic and dedicated DNN architectures suitable for state estimation, and provide a systematic presentation of techniques for fusing AI tools with KFs and for leveraging partial SS modeling and data, categorizing design approaches into task-oriented and SS model-oriented. The usefulness of each approach in preserving the individual strengths of model-based KFs and data-driven DNNs is investigated in a qualitative and quantitative study, whose code is publicly available, illustrating the gains of hybrid model-based/data-driven designs. We also discuss existing challenges and future research directions that arise from fusing AI and Kalman-type algorithms.

cs.LG↗

arXiv2024

MarkovType: A Markov Decision Process Strategy for Non-Invasive Brain-Computer Interfaces Typing Systems

Brain-Computer Interfaces (BCIs) help people with severe speech and motor disabilities communicate and interact with their environment using neural activity. This work focuses on the Rapid Serial Visual Presentation (RSVP) paradigm of BCIs using noninvasive electroencephalography (EEG). The RSVP typing task is a recursive task with multiple sequences, where users see only a subset of symbols in each sequence. Extensive research has been conducted to improve classification in the RSVP typing task, achieving fast classification. However, these methods struggle to achieve high accuracy and do not consider the typing mechanism in the learning procedure. They apply binary target and non-target classification without including recursive training. To improve performance in the classification of symbols while controlling the classification speed, we incorporate the typing setup into training by proposing a Partially Observable Markov Decision Process (POMDP) approach. To the best of our knowledge, this is the first work to formulate the RSVP typing task as a POMDP for recursive classification. Experiments show that the proposed approach, MarkovType, results in a more accurate typing system compared to competitors. Additionally, our experiments demonstrate that while there is a trade-off between accuracy and speed, MarkovType achieves the optimal balance between these factors compared to other methods.

cs.LG↗

arXiv2024

Learning Physics Informed Neural ODEs With Partial Measurements

Learning dynamics governing physical and spatiotemporal processes is a challenging problem, especially in scenarios where states are partially measured. In this work, we tackle the problem of learning dynamics governing these systems when parts of the system's states are not measured, specifically when the dynamics generating the non-measured states are unknown. Inspired by state estimation theory and Physics Informed Neural ODEs, we present a sequential optimization framework in which dynamics governing unmeasured processes can be learned. We demonstrate the performance of the proposed approach leveraging numerical simulations and a real dataset extracted from an electro-mechanical positioning system. We show how the underlying equations fit into our formalism and demonstrate the improved performance of the proposed method when compared with baselines.

cs.LG↗

arXiv2024

A Bayesian Framework for Clustered Federated Learning

One of the main challenges of federated learning (FL) is handling non-independent and identically distributed (non-IID) client data, which may occur in practice due to unbalanced datasets and use of different data sources across clients. Knowledge sharing and model personalization are key strategies for addressing this issue. Clustered federated learning is a class of FL methods that groups clients that observe similarly distributed data into clusters, such that every client is typically associated with one data distribution and participates in training a model for that distribution along their cluster peers. In this paper, we present a unified Bayesian framework for clustered FL which associates clients to clusters. Then we propose several practical algorithms to handle the, otherwise growing, data associations in a way that trades off performance and computational complexity. This work provides insights on client-cluster associations and enables client knowledge sharing in new ways. The proposed framework circumvents the need for unique client-cluster associations, which is seen to increase the performance of the resulting models in a variety of experiments.

cs.LG↗

arXiv2024

KODA: A Data-Driven Recursive Model for Time Series Forecasting and Data Assimilation using Koopman Operators

Approaches based on Koopman operators have shown great promise in forecasting time series data generated by complex nonlinear dynamical systems (NLDS). Although such approaches are able to capture the latent state representation of a NLDS, they still face difficulty in long term forecasting when applied to real world data. Specifically many real-world NLDS exhibit time-varying behavior, leading to nonstationarity that is hard to capture with such models. Furthermore they lack a systematic data-driven approach to perform data assimilation, that is, exploiting noisy measurements on the fly in the forecasting task. To alleviate the above issues, we propose a Koopman operator-based approach (named KODA - Koopman Operator with Data Assimilation) that integrates forecasting and data assimilation in NLDS. In particular we use a Fourier domain filter to disentangle the data into a physical component whose dynamics can be accurately represented by a Koopman operator, and residual dynamics that represents the local or time varying behavior that are captured by a flexible and learnable recursive model. We carefully design an architecture and training criterion that ensures this decomposition lead to stable and long-term forecasts. Moreover, we introduce a course correction strategy to perform data assimilation with new measurements at inference time. The proposed approach is completely data-driven and can be learned end-to-end. Through extensive experimental comparisons we show that KODA outperforms existing state of the art methods on multiple time series benchmarks such as electricity, temperature, weather, lorenz 63 and duffing oscillator demonstrating its superior performance and efficacy along the three tasks a) forecasting, b) data assimilation and c) state prediction.

cs.LG↗