arXiv subjects

Carlos T. Calafate

Publications and source records attributed to Carlos T. Calafate.

6 recordsLinked to original sources

arXiv2026

Wearable Data Profiling for NDN-Based Smart Healthcare: Performance Comparison with an IP Baseline

Smart healthcare IoT requires low-latency and reliable delivery of patient data, yet IP-based communication remains host-centric and offers limited support for mobility, caching, and request aggregation. This paper evaluates a smartphone-centric Named Data Networking (NDN) approach in which a patient's smartphone aggregates sensor streams and publishes a stable latest profile under a consistent name, enabling effective in-network caching. Using ndnSIM simulations on a realistic medical IoT topology, we compare NDN and IP under identical traffic and link conditions. Results show that per-sample naming provides little benefit, but smartphone aggregation with stable naming allows NDN caching to reduce delay after cache warm-up and achieve significantly higher delivery ratios under congestion compared to IP.

cs.NI↗

arXiv2026

Semantic Invariance in Agentic AI

Large Language Models (LLMs) increasingly serve as autonomous reasoning agents in decision support, scientific problem-solving, and multi-agent coordination systems. However, deploying LLM agents in consequential applications requires assurance that their reasoning remains stable under semantically equivalent input variations, a property we term semantic invariance. Standard benchmark evaluations, which assess accuracy on fixed, canonical problem formulations, fail to capture this critical reliability dimension. To address this shortcoming, in this paper we present a metamorphic testing framework for systematically assessing the robustness of LLM reasoning agents, applying eight semantic-preserving transformations (identity, paraphrase, fact reordering, expansion, contraction, academic context, business context, and contrastive formulation) across seven foundation models spanning four distinct architectural families: Hermes (70B, 405B), Qwen3 (30B-A3B, 235B-A22B), DeepSeek-R1, and gpt-oss (20B, 120B). Our evaluation encompasses 19 multi-step reasoning problems across eight scientific domains. The results reveal that model scale does not predict robustness: the smaller Qwen3-30B-A3B achieves the highest stability (79.6% invariant responses, semantic similarity 0.91), while larger models exhibit greater fragility.

cs.AI↗

arXiv2022

Signature and Log-signature for the Study of Empirical Distributions Generated with GANs

In this paper, we bring forward the use of the recently developed Signature Transform as a way to measure the similarity between image distributions and provide detailed acquaintance and extensive evaluations. We are the first to pioneer RMSE and MAE Signature, along with log-signature as an alternative to measure GAN convergence, a problem that has been extensively studied. We are also forerunners to introduce analytical measures based on statistics to study the goodness of fit of the GAN sample distribution that are both efficient and effective. Current GAN measures involve lots of computation normally done at the GPU and are very time consuming. In contrast, we diminish the computation time to the order of seconds and computation is done at the CPU achieving the same level of goodness. Lastly, a PCA adaptive t-SNE approach, which is novel in this context, is also proposed for data visualization.

cs.CV↗

arXiv2022

Fuel savings through missed approach maneuvers based on aircraft reinjection

Humanity is facing global challenges related to climate change, along with an energetic crisis that urgently requires optimizing any process or system able to improve global economic conditions. Taking fuel as an example, its prices are among the highest increases detected in goods of general use. In this sense, initiatives to mitigate fuel consumption are both welcome and necessary. In the aerial transportation area, fuel costs are critical to the economic viability of companies, and so urgent measures should be adopted to avoid any unnecessary increase of operational costs. In this work we study the costs involved in a standard procedure following a missed approach. In addition, we study the improvements achieved with a fast reinjection scheme proposed in a prior work. Experimental results show that, for a standard A320 aircraft, fuel savings ranging from 55% to 90% can be achieved through our proposed method.

eess.SY↗

arXiv2022

Learning with Signatures

In this work we investigate the use of the Signature Transform in the context of Learning. Under this assumption, we advance a supervised framework that potentially provides state-of-the-art classification accuracy with the use of few labels without the need of credit assignment and with minimal or no overfitting. We leverage tools from harmonic analysis by the use of the signature and log-signature, and use as a score function RMSE and MAE Signature and log-signature. We develop a closed-form equation to compute probably good optimal scale factors, as well as the formulation to obtain them by optimization. Techniques of Signal Processing are addressed to further characterize the problem. Classification is performed at the CPU level orders of magnitude faster than other methods. We report results on AFHQ, MNIST and CIFAR10, achieving 100% accuracy on all tasks assuming we can determine at test time which probably good optimal scale factor to use for each category.

cs.CV↗

arXiv2016

DrivingStyles: A mobile platform for driving styles and fuel consumption characterization

Intelligent Transportation Systems (ITS) rely on connected vehicle applications to address real-world problems. Research is currently being conducted to support safety, mobility and environmental applications. This paper presents the DrivingStyles architecture, which adopts data mining techniques and neural networks to analyze and generate a classification of driving styles and fuel consumption based on driver characterization. In particular, we have implemented an algorithm that is able to characterize the degree of aggressiveness of each driver. We have also developed a methodology to calculate, in real-time, the consumption and environmental impact of spark ignition and diesel vehicles from a set of variables obtained from the vehicle's Electronic Control Unit (ECU). In this paper, we demonstrate the impact of the driving style on fuel consumption, as well as its correlation with the greenhouse gas emissions generated by each vehicle. Overall, our platform is able to assist drivers in correcting their bad driving habits, while offering helpful tips to improve fuel economy and driving safety.

cs.CY↗