Searcharxiv⌕ Search

arXiv subjects

Luis Almeida

Publications and source records attributed to Luis Almeida.

At least 19 recordsLinked to original sources
arXiv2026

Graph Neural Assisted Actor-Critic for Latency-Efficient Edge Vision System

UAV on-board vision systems are widely used for different activities, including monitoring in no-fly zones. In this case, the vision-equipped UAV streams a video to a ground server where an operator assists its activities. The latency of video transmission has a profound impact on the effectiveness of the operator assistance. However, most techniques available for video transmission still incur significant latency costs. In this paper, we propose a graph convolutional neural network-assisted (GCN-Assisted A2C) deep reinforcement learning (DRL) system model to find the optimal pixel-correlated area of a suspicious object. We combine the Lagrangian dual form with gradient descent to prevent lack of convergence and over- and under-penalization constraint violation during latency optimization. The proposed system model sends a sub-group pixel-correlated area of the frame from the UAV to the server rather than the transmission of the whole video frame. The proposed framework utilizes the GCN model to explore hidden representations of feature-correlated groups of pixels. Moreover, the GCN supervises the A2C model, which selects a subgroup to enhance transmission latency, thus supervising the training of UAV actions in A2C. Experimental results show that GCN-assisted A2C reduces video frame transmission latency together with false detection rate in UAV vision systems over other DRL and state-of-the-art models.

cs.CV↗
arXiv2026

3D Weighted Geometric Graph Neural Networks for Sheep Facial Pain Assessment

Deep learning systems perform mainly within the 2D for a single image domain and take the face as a single-dimension representation, losing sight of the 3D anatomy of sheep and cross-landmark spatial relationships that are intrinsic to the clinically proven Sheep Pain Facial Expression Scale (SPFES). This paper presents the \textbf{3D Sheep Pain Facial Expression System (3D-SPFES)}, a novel, monocular depth-aware geometric graph neural network system that integrates each SPFES facial landmark, such as the ears, eyes, and nose, into 3D Euclidean space estimated from a single RGB camera by using VideoDepthAnything, thus preventing the need for specialized depth hardware. Each landmark node includes a feature vector containing its 3D spatial coordinates, estimated surface normal, and facial attribute class embedding. Edges linked to nodes are assigned weights based on an aggregate metric that combines both Euclidean distance and surface co-planarity in a 3D space. A Weighted Geometric Graph Neural Network (WG-GNN) studies this graph using $\mathcal{K} = 3$ geometry-aware message-passing layers enhanced by a scaled dot-product attention method that selectively enhances anatomically relevant inter-landmark messages. The resultant node embeddings are combined into $\mathcal{O} = 3$ pain-level clusters and integrated into a Normalized Pain Score (NPS) within the range of $[0, 100%]$ a confidence-weighted, SPFES-derived scoring method.

cs.CV↗
arXiv2026

Sterile mosquito release via intelligent proportional controllers

The Sterile Insect Technique (SIT) against insect pests and insect vectors consists of releasing males that have been previously sterilized in order to reduce or eliminate a specific wild population. We study this complex control question via model-free control, ultra-local models, and intelligent proportional controllers that have already proven their effectiveness in various fields. They permit addressing, perhaps for the first time, the essential sampling question. Computer simulations are displayed and discussed.

math.OC↗
arXiv2026

Large Language Model-Assisted UAV Operations and Communications: A Multifaceted Survey and Tutorial

Uncrewed Aerial Vehicles (UAVs) are widely deployed across diverse applications due to their mobility and agility. Recent advances in Large Language Models (LLMs) offer a transformative opportunity to enhance UAV intelligence beyond conventional optimization-based and learning-based approaches. By integrating LLMs into UAV systems, advanced environmental understanding, swarm coordination, mobility optimization, and high-level task reasoning can be achieved, thereby allowing more adaptive and context-aware aerial operations. This survey systematically explores the intersection of LLMs and UAV technologies and proposes a unified framework that consolidates existing architectures, methodologies, and applications for UAVs. We first present a structured taxonomy of LLM adaptation techniques for UAVs, including pretraining, fine-tuning, Retrieval-Augmented Generation (RAG), and prompt engineering, along with key reasoning capabilities such as Chain-of-Thought (CoT) and In-Context Learning (ICL). We then examine LLM-assisted UAV communications and operations, covering navigation, mission planning, swarm control, safety, autonomy, and network management. After that, the survey further discusses Multimodal LLMs (MLLMs) for human-swarm interaction, perception-driven navigation, and collaborative control. Finally, we address ethical considerations, including bias, transparency, accountability, and Human-in-the-Loop (HITL) strategies, and outline future research directions. Overall, this work positions LLM-assisted UAVs as a foundation for intelligent and adaptive aerial systems.

cs.RO↗
arXiv2025

Mechanistic-statistical inference of mosquito dynamics from mark-release-recapture data

Biological control strategies against mosquito-borne diseases--such as the sterile insect technique (SIT), RIDL, and Wolbachia-based releases--require reliable estimates of dispersal and survival of released males. We propose a mechanistic--statistical framework for mark--release--recapture (MRR) data linking an individual-based 2D diffusion model with its reaction--diffusion limit. Inference is based on solving the macroscopic system and embedding it in a Poisson observation model for daily trap counts, with uncertainty quantified via a parametric bootstrap. We validate identifiability using simulated data and apply the model to an urban MRR campaign in El Cano (Havana, Cuba) involving four weekly releases of sterile Aedes aegypti males. The best-supported model suggests a mean life expectancy of about five days and a typical displacement of about 180 m. Unlike empirical fits of survival or dispersal, our mechanistic approach jointly estimates movement, mortality, and capture, yielding biologically interpretable parameters and a principled framework for designing and evaluating SIT-based interventions.

q-bio.PE↗
arXiv2025

FRSICL: LLM-Enabled In-Context Learning Flight Resource Allocation for Fresh Data Collection in UAV-Assisted Wildfire Monitoring

Uncrewed Aerial Vehicles (UAVs) play a vital role in public safety, especially in monitoring wildfires, where early detection reduces environmental impact. In UAV-Assisted Wildfire Monitoring (UAWM) systems, jointly optimizing the data collection schedule and UAV velocity is essential to minimize the average Age of Information (AoI) for sensory data. Deep Reinforcement Learning (DRL) has been used for this optimization, but its limitations-including low sampling efficiency, discrepancies between simulation and real-world conditions, and complex training make it unsuitable for time-critical applications such as wildfire monitoring. Recent advances in Large Language Models (LLMs) provide a promising alternative. With strong reasoning and generalization capabilities, LLMs can adapt to new tasks through In-Context Learning (ICL), which enables task adaptation using natural language prompts and example-based guidance without retraining. This paper proposes a novel online Flight Resource Allocation scheme based on LLM-Enabled In-Context Learning (FRSICL) to jointly optimize the data collection schedule and UAV velocity along the trajectory in real time, thereby asymptotically minimizing the average AoI across all ground sensors. Unlike DRL, FRSICL generates data collection schedules and velocities using natural language task descriptions and feedback from the environment, enabling dynamic decision-making without extensive retraining. Simulation results confirm the effectiveness of FRSICL compared to state-of-the-art baselines, namely Proximal Policy Optimization, Block Coordinate Descent, and Nearest Neighbor.

cs.AI↗
arXiv2025

From Prompts to Protection: Large Language Model-Enabled In-Context Learning for Smart Public Safety UAV

A public safety Uncrewed Aerial Vehicle (UAV) enhances situational awareness during emergency response. Its agility, mobility optimization, and ability to establish Line-of-Sight (LoS) communication make it increasingly important for managing emergencies such as disaster response, search and rescue, and wildfire monitoring. Although Deep Reinforcement Learning (DRL) has been used to optimize UAV navigation and control, its high training complexity, low sample efficiency, and the simulation-to-reality gap limit its practicality in public safety applications. Recent advances in Large Language Models (LLMs) present a promising alternative. With strong reasoning and generalization abilities, LLMs can adapt to new tasks through In-Context Learning (ICL), enabling task adaptation via natural language prompts and example-based guidance without retraining. Deploying LLMs at the network edge, rather than in the cloud, further reduces latency and preserves data privacy, making them suitable for real-time, mission-critical public safety UAVs. This paper proposes integrating LLM-assisted ICL with public safety UAVs to address key functions such as path planning and velocity control in emergency response. We present a case study on data collection scheduling, demonstrating that the LLM-assisted ICL framework can significantly reduce packet loss compared to conventional approaches while also mitigating potential jailbreaking vulnerabilities. Finally, we discuss LLM optimizers and outline future research directions. The ICL framework enables adaptive, context-aware decision-making for public safety UAVs, offering a lightweight and efficient solution to enhance UAV autonomy and responsiveness in emergencies.

cs.AI↗
arXiv2025

Sheep Facial Pain Assessment Under Weighted Graph Neural Networks

Accurately recognizing and assessing pain in sheep is key to discern animal health and mitigating harmful situations. However, such accuracy is limited by the ability to manage automatic monitoring of pain in those animals. Facial expression scoring is a widely used and useful method to evaluate pain in both humans and other living beings. Researchers also analyzed the facial expressions of sheep to assess their health state and concluded that facial landmark detection and pain level prediction are essential. For this purpose, we propose a novel weighted graph neural network (WGNN) model to link sheep's detected facial landmarks and define pain levels. Furthermore, we propose a new sheep facial landmarks dataset that adheres to the parameters of the Sheep Facial Expression Scale (SPFES). Currently, there is no comprehensive performance benchmark that specifically evaluates the use of graph neural networks (GNNs) on sheep facial landmark data to detect and measure pain levels. The YOLOv8n detector architecture achieves a mean average precision (mAP) of 59.30% with the sheep facial landmarks dataset, among seven other detection models. The WGNN framework has an accuracy of 92.71% for tracking multiple facial parts expressions with the YOLOv8n lightweight on-board device deployment-capable model.

cs.CV↗
arXiv2025

LLM-Enabled In-Context Learning for Data Collection Scheduling in UAV-assisted Sensor Networks

Unmanned Aerial Vehicles (UAVs) are increasingly being utilized in various private and commercial applications, e.g., traffic control, parcel delivery, and Search and Rescue (SAR) missions. Machine Learning (ML) methods used in UAV-Assisted Sensor Networks (UASNETs) and, especially, in Deep Reinforcement Learning (DRL) face challenges such as complex and lengthy model training, gaps between simulation and reality, and low sampling efficiency, which conflict with the urgency of emergencies, such as SAR missions. In this paper, an In-Context Learning (ICL)-Data Collection Scheduling (ICLDC) system is proposed as an alternative to DRL in emergencies. The UAV collects sensory data and transmits it to a Large Language Model (LLM), which creates a task description in natural language. From this description, the UAV receives a data collection schedule that must be executed. A verifier ensures safe UAV operations by evaluating the schedules generated by the LLM and overriding unsafe schedules based on predefined rules. The system continuously adapts by incorporating feedback into the task descriptions and using this for future decisions. This method is tested against jailbreaking attacks, where the task description is manipulated to undermine network performance, highlighting the vulnerability of LLMs to such attacks. The proposed ICLDC significantly reduces cumulative packet loss compared to both the DQN and Maximum Channel Gain baselines. ICLDC presents a promising direction for intelligent scheduling and control in UASNETs.

cs.AI↗
arXiv2025

Diffusion Models for Smarter UAVs: Decision-Making and Modeling

Uncrewed Aerial Vehicles (UAVs) are increasingly used in modern communication networks. However, challenges in decision-making and digital modeling continue to hinder their rapid development. Reinforcement Learning (RL) algorithms face limitations such as low sample efficiency and limited data versatility, which are further amplified in UAV communications scenarios. Additionally, Digital Twin (DT) modeling presents significant challenges in decision-making and data management. RL models, often integrated into DT frameworks to address these issues, require large amounts of training data to make accurate predictions. Unlike traditional approaches that focus on class boundaries, Diffusion Models (DMs)-a new class of generative AI-learn the underlying probability distribution from training data and can generate reliable new patterns based on this learned distribution. DT and RL have complementary roles in enabling intelligent, data-driven UAV operations. DMs further enhance this synergy by addressing data scarcity, improving modeling accuracy, and generating realistic scenarios, which benefit both DT simulations and RL training. In this paper, we explore the integration of DMs with RL and DT. Simulation results confirm the effectiveness and benefits of DMs in generating neighbor velocity estimates in a four-UAV swarm coordination task using Deep Reinforcement Learning (DRL).

cs.LG↗
arXiv2024

Analysis of a toy model for optimal crop protection

In this paper we investigate an optimal control problem involving a toy model for the protection on a crop field. Precisely, we consider a protection on a crop field and we want to place intervention zones represented by a control, in order to maximise the protection on the field during a given period. Using a relaxation method, we prove that there exists a control which maximises the protection and, moreover, it must be a bang-bang control. Furthermore, with additional assumptions on the crop field geometry, some results on the shape of the optimal intervention are proved using comparison results for elliptic equations via Schwarz and Steiner symmetrizations. Finally, some numerical simulations are performed in order to illustrate those results.

math.OC↗
arXiv2024

Human-In-The-Loop Machine Learning for Safe and Ethical Autonomous Vehicles: Principles, Challenges, and Opportunities

Machine Learning (ML) has become central to Autonomous Vehicles (AVs), supporting perception, prediction, planning, control, and decision-making in dynamic environments. However, achieving full autonomy in cluttered and complex scenarios, such as intricate intersections, diverse scenes, varied trajectories, and complex missions, remains challenging; moreover, data labeling is still a major bottleneck. These limitations motivate Human-in-the-Loop Machine Learning (HITL-ML), in which human input is incorporated through validation, annotation, task organization, reward design, action correction, preference feedback, and supervisory intervention. To advance safe and ethical autonomy, this paper presents a tutorial survey of HITL-ML for AVs, focusing on Curriculum Learning (CL), Human-in-the-Loop Reinforcement Learning (HITL-RL), Human-in-the-Loop Large Language Models (HITL-LLMs), Active Learning (AL), and ethical principles. We first review CL methods that structure training from simple to complex tasks, covering navigation, path planning, obstacle avoidance, data collection, landing, intersection handling, motion planning, and UAV swarm coordination. We then examine HITL-RL through reward shaping, action injection, demonstrations, preference-based feedback, and interactive learning, emphasizing improved learning efficiency, safer policy exploration, and real-time intervention. Next, we review HITL-LLM through collaboration and oversight and specify key challenges. After that, we discuss AL for perception, anomaly detection, semantic mapping, object detection, vehicle recognition, and security-related classification. Ethical principles are reviewed as technical requirements for transparency, accountability, human oversight, safety, security, regulatory compliance, and reliability of human input.

cs.LG↗
arXiv2024

Age of Information Minimization using Multi-agent UAVs based on AI-Enhanced Mean Field Resource Allocation

Unmanned Aerial Vehicle (UAV) swarms play an effective role in timely data collection from ground sensors in remote and hostile areas. Optimizing the collective behavior of swarms can improve data collection performance. This paper puts forth a new mean field flight resource allocation optimization to minimize age of information (AoI) of sensory data, where balancing the trade-off between the UAVs movements and AoI is formulated as a mean field game (MFG). The MFG optimization yields an expansive solution space encompassing continuous state and action, resulting in significant computational complexity. To address practical situations, we propose, a new mean field hybrid proximal policy optimization (MF-HPPO) scheme to minimize the average AoI by optimizing the UAV's trajectories and data collection scheduling of the ground sensors given mixed continuous and discrete actions. Furthermore, a long short term memory (LSTM) is leveraged in MF-HPPO to predict the time-varying network state and stabilize the training. Numerical results demonstrate that the proposed MF-HPPO reduces the average AoI by up to 45 percent and 57 percent in the considered simulation setting, as compared to multi-agent deep Q-learning (MADQN) method and non-learning random algorithm, respectively.

eess.SY↗
arXiv2023

Optimal strategies for Wolbachia mosquito replacement technique: influence of the carrying capacity on spatial releases

This work is devoted to the mathematical study of an optimization problem regarding control strategies of mosquito population in a heterogeneous environment. Mosquitoes are well-known vectors of diseases. For some diseases, such as dengue, it has been found that mosquitoes have a reduced vector capacity when carrying the endosymbiotic bacterium Wolbachia. We consider a mathematical model of a replacement technique consisting in rearing and releasing Wolbachia-infected mosquitoes to replace the wild population. Our goal is to optimize the release protocol to maximize replacement effectiveness in a spatially inhomogeneous environment. Using a scalar model with space-dependent carrying capacity, we explore the existence and properties of an optimal release profile maximizing the replacement across the domain. In particular, neglecting mosquito mobility and under some assumptions on the biological parameters, we characterize the optimal releasing strategy for a short time horizon, and we reduce the case of a long time horizon to a one-dimensional optimization problem. Our theoretical results are illustrated with several numerical simulations.

math.OC↗
arXiv2023

An individual-based model to explore the impact of psychological stress on immune infiltration into tumour spheroids

In recent in vitro experiments on co-culture between breast tumour spheroids and activated immune cells, it was observed that the introduction of the stress hormone cortisol resulted in a decreased immune cell infiltration into the spheroids. Moreover, the presence of cortisol deregulated the normal levels of the pro- and anti-inflammatory cytokines IFN-{\gamma} and IL-10. We present an individual-based model to explore the interaction dynamics between tumour and immune cells under psychological stress conditions. With our model, we explore the processes underlying the emergence of different levels of immune infiltration, with particular focus on the biological mechanisms regulated by IFN-{\gamma} and IL-10. The set-up of numerical simulations is defined to mimic the scenarios considered in the experimental study. Similarly to the experimental quantitative analysis, we compute a score that quantifies the level of immune cell infiltration into the tumour. The results of numerical simulations indicate that the motility of immune cells, their capability to infiltrate through tumour cells, their growth rate and the interplay between these cell parameters can affect the level of immune cell infiltration in different ways. Ultimately, numerical simulations of this model support a deeper understanding of the impact of biological stress-induced mechanisms on immune infiltration.

q-bio.CB↗
arXiv2023

Vector-borne disease outbreak control via instant releases

This paper is devoted to the study of optimal release strategies to control vector-borne diseases, such as dengue, Zika, chikungunya and malaria. Two techniques are considered: the sterile insect one (SIT), which consists in releasing sterilized males among wild vectors in order to perturb their reproduction, and the Wolbachia one (presently used mainly for mosquitoes), which consists in releasing vectors, that are infected with a bacterium limiting their vector capacity, in order to replace the wild population by one with reduced vector capacity. In each case, the time dynamics of the vector population is modeled by a system of ordinary differential equations in which the releases are represented by linear combinations of Dirac measures with positive coefficients determining their intensity. We introduce optimal control problems that we solve numerically using ad-hoc algorithms, based on writing first-order optimality conditions characterizing the best combination of Dirac measures. We then discuss the results obtained, focusing in particular on the complexity and efficiency of optimal controls and comparing the strategies obtained. Mathematical modeling can help testing a great number of scenarios that are potentially interesting in future interventions (even those that are orthogonal to the present strategies) but that would be hard, costly or even impossible to test in the field in present conditions.

math.OC↗
arXiv2023

Evolutionary dynamics of glucose-deprived cancer cells: insights from experimentally-informed mathematical modelling

Glucose is a primary energy source for cancer cells. Several lines of evidence support the idea that monocarboxylate transporters, such as MCT1, elicit metabolic reprogramming of cancer cells in glucose-poor environments, allowing them to reuse lactate, a byproduct of glucose metabolism, as an alternative energy source with serious consequences for disease progression. We employ a synergistic experimental and mathematical modelling approach to explore the evolutionary processes at the root of cancer cell adaptation to glucose deprivation, with particular focus on the mechanisms underlying the increase in MCT1 expression observed in glucose-deprived aggressive cancer cells. Data from in vitro experiments on breast cancer cells are used to inform and calibrate a mathematical model that comprises a partial integro-differential equation for the dynamics of a population of cancer cells structured by the level of MCT1 expression. Analytical and numerical results of this model suggest that environment-induced changes in MCT1 expression mediated by lactate-associated signalling pathways enable a prompt adaptive response of glucose-deprived cancer cells, whilst fluctuations in MCT1 expression due to epigenetic changes create the substrate for environmental selection to act upon, speeding up the selective sweep underlying cancer cell adaptation to glucose deprivation, and may constitute a long-term bet-hedging mechanism.

q-bio.CB↗
arXiv2022

A hybrid discrete-continuum modelling approach to explore the impact of T-cell infiltration on anti-tumour immune response

We present a spatial hybrid discrete-continuum modelling framework for the interaction dynamics between tumour cells and cytotoxic T cells, which play a pivotal role in the immune response against tumours. In this framework, tumour cells and T cells are modelled as individual agents while chemokines that drive the chemotactic movement of T cells towards the tumour are modelled as a continuum. We formally derive the continuum counterpart of this model, which is given by a coupled system that comprises an integro-differential equation for the density of tumour cells, a partial differential equation for the density of T cells, and a partial differential equation for the concentration of chemokines. We report on computational results of the hybrid model and show that there is an excellent quantitative agreement between them and numerical solutions of the corresponding continuum model. These results shed light on the mechanisms that underlie the emergence of different levels of infiltration of T cells into the tumour and elucidate how T-cell infiltration shapes anti-tumour immune response. Moreover, to present a proof of concept for the idea that, exploiting the computational efficiency of the continuum model, extensive numerical simulations could be carried out, we investigate the impact of T-cell infiltration on the response of tumour cells to different types of anti-cancer immunotherapy.

math.AP↗