AggRaDa is a framework designed to automate the spatiotemporal aggregation of heterogeneous raw data from multiple sources. Its purpose is to automatically identify granularities that maximize the consistency and representativeness of the data, making them more useful for analysis and decision-making. The modular microservices-based architecture integrates indexing and manipulation of spatial and temporal data, enabling efficient exploration of multiple scales and quantitative evaluation of the results.

Automatic spatiotemporal aggregation of multi-source heterogeneous raw data at multiple granularities.

large_aggrada_thumbnail.webp

medium_aggrada_thumbnail.webp

small_aggrada_thumbnail.webp

thumbnail_aggrada_thumbnail.webp

aggrada_thumbnail.webp

AggRaDa - Aggregation of Raw Data

The current core (of Almes) focuses on providing a detailed description of agricultural price index datasets.
The Almes Core Reference Guide defines metadata and provides structured data with vocabulary schemes like Agrovoc and Agrotermos. 

Agriculture and Livestock Metadata Elements Set., fundamental for a Confident and Broad AI.

large_almescore_thumbnail.webp

medium_almescore_thumbnail.webp

small_almescore_thumbnail.webp

thumbnail_almescore_thumbnail.webp

almescore_thumbnail.webp

Almes-core

An ontology of types (or a classification ontology), meaning it does not contain individuals and is intended as a classification system for agricultural commodities price index databases in Brazil. 

large_apto_d58b87edb6.webp

medium_apto_d58b87edb6.webp

small_apto_d58b87edb6.webp

thumbnail_apto_d58b87edb6.webp

apto_d58b87edb6.webp

APTO

Evaluation of school food menu IQCAE-R supported by text mining techniques

large_autoicaer_thumb.webp

medium_autoicaer_thumb.webp

small_autoicaer_thumb.webp

thumbnail_autoicaer_thumb.webp

autoicaer_thumb.webp

Automated IQCAE-R

Constructing elementary cell of Cellular Neural Networks (CelNN) in an IBM physical quantum computer. An elementary cell works as a Full Adder for digital computers. CelNN are among a dozen candidates for quantum NN.

CellNN has high locality and cells that can use low amounts of qubits, which may enable them in a Noise-Intermediate State Quantum (NISQ) device. 

medium_Screenshot_2024_09_12_at_09_51_50_21f02e1b9a.png

small_Screenshot_2024_09_12_at_09_51_50_21f02e1b9a.png

thumbnail_Screenshot_2024_09_12_at_09_51_50_21f02e1b9a.png

Screenshot_2024_09_12_at_09_51_50_21f02e1b9a.png

CelNN in a quantum device

Exploring randomness generation across computational and physical processes:  pseudorandom algorithms and hardware, data collected from Nature, and from different quantum-device technologies. 

Evaluate randomness from diverse technologies

large_Generazione Casuale Diversificata.png

medium_Generazione Casuale Diversificata.png

small_Generazione Casuale Diversificata.png

thumbnail_Generazione Casuale Diversificata.png

Generazione Casuale Diversificata.png

chaosStat

Environmental monitoring platform that integrates technology, education, and citizen science to promote urban sustainability and social engagement.

large_thumb_clickclima_v3.png

medium_thumb_clickclima_v3.png

small_thumb_clickclima_v3.png

thumbnail_thumb_clickclima_v3.png

thumb_clickclima_v3.png

ClickClima

Innovative tool that uses FAIR quality metrics, Openness, and data maturity to automatically assess the quality and transparency of databases through the attribution of scores and detailed reports.

Automatically evaluate databases quality and transparency.

large_dbscore_thumb.webp

medium_dbscore_thumb.webp

small_dbscore_thumb.webp

thumbnail_dbscore_thumb.webp

dbscore_thumb.webp

DBScore

By using data from Brazilian school meals, It elaborates a portfolio of food menus with a tradeoff among nutrition indicators, the variety of components, and the prioritization of organics and regional products. 

Generation of improved menus from Brazilian school meal data by multiobjective optimization and autoencoders

large_Recomendacao_de_cardapios_escolares_versao_2_Img0_ffcb7829f3.png

medium_Recomendacao_de_cardapios_escolares_versao_2_Img0_ffcb7829f3.png

small_Recomendacao_de_cardapios_escolares_versao_2_Img0_ffcb7829f3.png

thumbnail_Recomendacao_de_cardapios_escolares_versao_2_Img0_ffcb7829f3.png

Recomendacao_de_cardapios_escolares_versao_2_Img0_ffcb7829f3.png

Food-Menus

Development of an automatic calibration strategy for flood models using multiobjective evolutionary optimization algorithms to enrich watershed data. Models can be knowledge-based, data-driven, and hybrid. 

Spatially-informed multiobjective optimization for integrating multi-source heterogeneous data and flood models

large_emergency_4314503_1920_9df6e4b256.png

medium_emergency_4314503_1920_9df6e4b256.png

small_emergency_4314503_1920_9df6e4b256.png

thumbnail_emergency_4314503_1920_9df6e4b256.png

emergency_4314503_1920_9df6e4b256.png

Hetero-Flood

This project provides a structured validation framework to assess whether a large language model (LLM) used in healthcare can safely classify a case as emergency, urgent, routine, or self-care, identify warning signs, and remain reliable under realistic stress conditions such as noisy input, lay language, conflicting information, and manipulation attempts. Its purpose is to reduce risk before deployment by generating objective evidence for go/no-go decisions, procurement, governance, and audit. This need is consistent with the World Health Organization’s guidance on the governance of generative AI in health.

Safety and Robustness Validation of LLMs for Clinical Triage

large_medeval-triage-thumbnail.webp

medium_medeval-triage-thumbnail.webp

small_medeval-triage-thumbnail.webp

thumbnail_medeval-triage-thumbnail.webp

medeval-triage-thumbnail.webp

MedEval Triage

This work focuses on Heterogeneous Data System Models (MsHD) for integrating complex, multidisciplinary data, often using geospatial data and choropleth maps to simplify analysis. Automating the creation of these maps through machine learning can improve decision-making, especially in critical situations. The MultiMapas system supports this process with six key modules, including geolocation, data aggregation, thematic layers, decision-making, visualization, and data repository.

Multiobjective generator of choropleth maps from heterogeneous multisource data

medium_Screenshot_2024_09_12_at_20_54_42_da587467ad.png

small_Screenshot_2024_09_12_at_20_54_42_da587467ad.png

thumbnail_Screenshot_2024_09_12_at_20_54_42_da587467ad.png

Screenshot_2024_09_12_at_20_54_42_da587467ad.png

Multimaps

Siflor4Decision is a tool for the analysis and visualization of models generated by the DAMICORE methodology from the SiFlor Cerrado system.

Multicriteria decision-making tool  from SiFlor-Cerrado System

large_DALL_E_2024_09_16_10_56_27_A_forest_scene_with_sunlight_streaming_through_the_trees_similar_to_the_previous_image_but_instead_of_a_Bayesian_structure_model_there_is_a_large_p_13d9176390.webp

medium_DALL_E_2024_09_16_10_56_27_A_forest_scene_with_sunlight_streaming_through_the_trees_similar_to_the_previous_image_but_instead_of_a_Bayesian_structure_model_there_is_a_large_p_13d9176390.webp

small_DALL_E_2024_09_16_10_56_27_A_forest_scene_with_sunlight_streaming_through_the_trees_similar_to_the_previous_image_but_instead_of_a_Bayesian_structure_model_there_is_a_large_p_13d9176390.webp

thumbnail_DALL_E_2024_09_16_10_56_27_A_forest_scene_with_sunlight_streaming_through_the_trees_similar_to_the_previous_image_but_instead_of_a_Bayesian_structure_model_there_is_a_large_p_13d9176390.webp

DALL_E_2024_09_16_10_56_27_A_forest_scene_with_sunlight_streaming_through_the_trees_similar_to_the_previous_image_but_instead_of_a_Bayesian_structure_model_there_is_a_large_p_13d9176390.webp

Siflor4Decision

Cellular Neural Networks (CelNN) for Evolutionary Partial Differential Equations enable dealing with complex (chaotic) systems from Nature, producing a kind of unsupervised Physics-Informed Neural Network.

Recent advances in Cellular Neural Networks (CelNN) for Evolutionary Partial Differential Equations provide solutions to complex and chaotic systems found in Nature.

Projects

Demo Outreach of MClimate/AgriBio and Other Major Projects