Making cities smarter is usually achieved through Information and Communication Technology (ICT)-intensive solutions, which can be employed to collect and analyze large amounts of information generated by several sources, such as sensor networks, traffic systems, and citizens' devices. However, integrating different technologies and information to build smart city applications and services remain a challenge as different sources of heterogeneous data need to be considered. These data can be also enriched with geospatial information, thereby generating cross-sector value-added information while contributing to better planning actions in the urban space. In this context, we introduce a data integration approach upon Smart Geo Layers, a geospatial-based data middleware aimed to unify data provided by several sources in smart city environments. Along with geo-graphical information regarding the city physical space, Smart Geo Layers provides aggregation, visualization, and data analysis functionalities. In this paper, we describe the Smart Geo Layers middleware, its implementation, and its application through an urban planning application within the smart city initiative of Natal, Brazil.
Background/Objectives: Repetitive behaviors such as hand flapping, body rocking, and head shaking characterize Autism Spectrum Disorder (ASD) while functioning as early signs of neurodevelopmental variations. Traditional diagnostic procedures require extensive manual observation, which takes significant time, produces subjective results, and remains unavailable to many regions. The research introduces a real-time system for the detection of ASD-typical behaviors by analyzing body movements through the You Only Look Once (YOLOv11) deep learning model. Methods: The system’s multi-layered design integrates monitoring, network, cloud, and typical ASD behavior detection layers to facilitate real-time video acquisition, wireless data transfer, and cloud analysis along with ASD-typical behavior classification. We gathered and annotated our own dataset comprising 72 videos, yielding a total of 13,640 images representing four behavior classes that include hand flapping, body rocking, head shaking, and non_autistic. Results: YOLOv11 demonstrates superior performance compared to baseline models like the sub-sampling (CNN) (MobileNet-SSD) and Long Short-Term Memory (LSTM) by achieving 99% accuracy along with 96% precision and 97% in recall and the F1-score. Conclusions: The results indicate that our system provides a scalable solution for real-time ASD screening, which might help clinicians, educators, and caregivers with early intervention, as well as ongoing behavioral monitoring.
The cloud lock-in problem is commonly addressed by three strategies: (i) use of intermediate layer between cloud services consumers and providers, (ii) use of standardized interfaces to access cloud services, or (iii) use of models with open specifications. This paper evaluated these strategies and concluded that despite the advances they introduced, none of them actually solves the cloud lock-in problem. To address this issue, this paper proposes the use of Semantic Web concepts to avoid cloud lock-in. The strategy consists of using RDF models to specify the features of a cloud service, which are managed by SPARQL queries. The contribution of this paper is fourfold: (i) to evaluate three multi-cloud solutions for the cloud lock-in problem in the context of three cloud platforms, (ii) to propose a strategy using RDF and SPARQL for managing cloud resources, (iii) to present the Cloud Query Manager (CQM), an SPARQL server that implements the proposal, and (vi) to compare three multi-cloud solutions with CQM in terms of response time and the effectiveness in the resolution of the cloud lock-in problem.