Percorrer por autor "Oliveira, Francisco"
A mostrar 1 - 5 de 5
Resultados por página
Opções de ordenação
- Analysis of ground reaction force and electromyographic activity of the gastrocnemius muscle during double supportPublication . Sousa, Andreia S. P.; Santos, Rubim; Oliveira, Francisco; Carvalho, Paulo; Tavares, João ManuelPurpose: Mechanisms associated with energy expenditure during gait have been extensively researched and studied. According to the double-inverted pendulum model energy expenditure is higher during double support, as lower limbs need to work to redirect the centre of mass velocity. This study looks into how the ground reaction force (GRF) of one limb affects the muscle activity required by the medial gastrocnemius (MG) of the contralateral limb during step-to-step transition. Methods: Thirty-five subjects were monitored as to the MG electromyographic activity (EMGa) of one limb and the GRF of the contralateral limb during double support. Results: After determination of the Pearson correlation coefficient (r), a moderate correlation was observed between the MG EMGa of the dominant leg and the vertical (Fz) and anteroposterior (Fy) components of GRF of the non-dominant leg (r=0.797, p<0.0001; r=-0.807, p<0.0001) and a weak and moderate correlation was observed between the MG EMGa of the non-dominant leg and the Fz and Fy of the dominant leg, respectively (r=0.442, p=0.018; r=-0.684 p<0.0001). Conclusions: The results obtained suggest that during double support, GRF is associated with the EMGa of the contralateral MG and that there is an increased dependence between the GRF of the non-dominant leg and the EMGa of the dominant MG.
- Automated extraction of insurance product characteristicsPublication . Oliveira, Francisco; Sousa, Paulo Gandra de; Faria, Luiz; Faria, Luiz; Cardoso, Duarte; Teixeira, JoãoThe increasing complexity and diversity of insurance products have highlighted the need for efficient methods to interpret and manage the detailed information present in regulatory documents. This project explores the application of Natural Language Processing (NLP) and Large Language Models (LLMs) in the automatic extraction of relevant characteristics of these products, addressing challenges such as structuring technical texts and accurately identifying rules, conditions, and variations. The research focuses on analyzing the state of the art in technologies such as vector databases, LLMs, knowledge graphs, and agentic workflows, as well as evaluating NLP tools and methodologies. The text goes on to explore the primary challenges encountered during the interpretation of insurance documentation, as well as the transformation of unstructured data into organized formats that are compatible with modelling systems. The solution developed responded satisfactorily to the objectives established, enabling the structured and consistent extraction of product characteristics from regulatory documents. To this end, AI agent-based workflows were used, supported by LLMs and validation schemes, ensuring the quality and consistency of the results.
- Simplifying complex insurance product management with AIPublication . Teixeira, João; Sousa, Paulo Gandra de; Cardoso, Duarte; Faria, Luiz; Oliveira, FranciscoThe digital transformation of the insurance sector presents significant challenges in internal processes, particularly in the management of product information. These challenges arise from the high complexity and variability of insurance product models, which are frequently updated, and from the technical demands of existing tools that require extensive user expertise to operate effectively. Recent advances in Generative Artificial Intelligence (GenAI) and the growing use of Large Language Models (LLMs) and intelligent agents are opening up new opportunities to automate and streamline processes, enabling organizations to adapt to a rapidly evolving technological landscape. The Product Machine Explorer leverages Generative AI, Large Language Models (LLMs), and AI agents to make exploring insurance product models easier. Integrated with msg Life Iberia’s Product Machine platform, it allows users to interact with complex product data using natural language. By leveraging structured data and advanced query techniques, it can understand user requests and deliver accurate, context-aware responses, improving both efficiency and usability in product model exploration. Built using the Evaluation-Driven Development (EDD) methodology and supported by software, prompt, and context engineering, the tool was assessed using defined metrics and expert feedback. The results demonstrate significant efficiency improvements, with professionals spending considerably less time on repetitive tasks. Overall, the Product Machine Explorer demonstrates how LLM-powered agents can simplify complex information management and support better decision-making in the insurance sector.
- Spatio-temporal alignment of pedobarographic image sequencesPublication . Oliveira, Francisco; Sousa, Andreia S. P.; Santos, Rubim; Tavares, João ManuelThis paper presents a methodology to align plantar pressure image sequences simultaneously in time and space. The spatial position and orientation of a foot in a sequence are changed to match the foot represented in a second sequence. Simultaneously with the spatial alignment, the temporal scale of the first sequence is transformed with the aim of synchronizing the two input footsteps. Consequently, the spatial correspondence of the foot regions along the sequences as well as the temporal synchronizing is automatically attained, making the study easier and more straightforward. In terms of spatial alignment, the methodology can use one of four possible geometric transformation models: rigid, similarity, affine or projective. In the temporal alignment, a polynomial transformation up to the 4th degree can be adopted in order to model linear and curved time behaviors. Suitable geometric and temporal transformations are found by minimizing the mean squared error (MSE) between the input sequences. The methodology was tested on a set of real image sequences acquired from a common pedobarographic device. When used in experimental cases generated by applying geometric and temporal control transformations, the methodology revealed high accuracy. Additionally, the intra-subject alignment tests from real plantar pressure image sequences showed that the curved temporal models produced better MSE results (p<0.001) than the linear temporal model. This paper represents an important step forward in the alignment of pedobarographic image data, since previous methods can only be applied on static images.
- Towards an efficient and robust foot classification from pedobarographic imagesPublication . Oliveira, Francisco; Sousa, Andreia S. P.; Santos, Rubim; Tavares, João ManuelThis paper presents a new computational framework for automatic foot classification from digital plantar pressure images. It classifies the foot as left or right and simultaneously calculates two well-known footprint indices: the Cavanagh's arch index and the modified arch index. The accuracy of the framework was evaluated using a set of plantar pressure images from two common pedobarographic devices. The results were outstanding, since all feet under analysis were correctly classified as left or right and no significant differences were observed between the footprint indices calculated using the computational solution and the traditional manual method. The robustness of the proposed framework to arbitrary foot orientations and to the acquisition device was also tested and confirmed.