Search

Educational institutions are moving to a hybrid model that allows onsite and online classes. Students and teachers must adapt to these changes in the teaching and learning routine, leading them to stress and anxiety moments. This work proposes an architecture to assist academics in detecting these stressful moments during daily activities. The proposal uses smart bands, machine learning algorithms, and a smartphone app for environment monitoring. The evaluation was conducted by collecting real data from heart rate spikes and enriching it using the location information to send recommendations. The results show that it is possible to identify stressful moments by respecting the academics environment by monitoring their routine.

Com a popularização de sensores vestíveis cada vez mais disseminada, a observação de dados corporais se tornou ainda mais pertinente. Por meio do estudo dos dados fornecidos por tais sensores, juntamente com dados de localização, para enriquecer as análises, somos capazes de detectar situações de estresse. Para que tal tarefa seja exequível, é necessária uma arquitetura robusta que comporte o volume de dados a serem consumidos pelos sistemas que detectam tais situações. Dessa forma, este trabalho apresenta uma proposta de arquitetura Fog-Cloud que faz uso de dados corporais e de localização por meio de técnicas de Machine Learning para determinar momentos de estresse do usuário.

The complexity imposed by data heterogeneity makes it difficult to integrate 'streaming x streaming' and 'streaming x historical' data types. For practical analysis, the enrichment and contextualization process based on historical and streaming data would benefit from approaches that facilitate data integration, abstracting details and formats of the primary sources. This work presents a framework that allows the integration of streaming data and historical data in real-time, abstracting syntactic aspects of queries through the use of SQL as a standard language for querying heterogeneous sources. The framework was evaluated through an experiment using a relational database and real data produced by sensors. The results point to the feasibility of the approach.