Smart Governance is a key pillar of the City movement and an important pathway to achieving Sustainable Development Goals through digital transformation technologic tools. However, highly contextual solutions from Global North may not be adequate reality developing countries. We present how tools policies, as part broader agenda for transformation, can touch upon several sustainability goals when focused on benefitting vulnerable citizens. Examples come observing process, stakeholders...

Irrigation is one of the most water-intensive agricultural activities in world, which has been increasing over time. Choosing an optimal irrigation management plan depends on having available data monitoring field. A smart agriculture system gathers from several sources; however, are not guaranteed to be free discrepant values (i.e., outliers), can damage precision management. Furthermore, different sources must fit into same temporal window required for and preprocessing dynamic automatic...

Many nations still struggle to provide their populations with access food and balanced nutrition. The Food Agriculture Organization of the United Nations (FAO) included Brazil in its 2022 Hunger Map, highlighting that 61 million Brazilians face difficulties feeding themselves. Despite presence various security alert monitoring systems food-insecure countries, data methodologies they rely on capture only a fraction issue’s complexity, underscoring need for further research fully comprehend...

Movement tracking becomes ubiquitous in many applications, which raises great interests trajectory data analysis and mining. Most existing approaches cluster the whole trajectories offline. This allows characterizing past movements of objects but not current patterns. Recent for online clustering moving location are restricted to instantaneous positions. Subsequently, they fail capture objects' behavior over time. By continuously sub-trajectories at each time window, rather than just last...

We consider the problem of efficiently discovering and detecting frequent mobility patterns on moving object data. Our proposed approach is key for applications, such as applications that need to discover explain movement a set objects (e.g. traffic management, birds migration, disease spreading). In this sense, we developed method performs density based clustering trajectory data at regular time intervals, then analyze clusters evolution, which characterized by appear, disappear, expand,...

Trajectory pattern mining allows characterizing movement behavior, which leverages new applications and services. Most existing approaches analyse the whole object trajectory rather that current movement. Besides for online discovery are restricted to instantaneous positions. Subsequently, they fail capture behaviour along time. By continuously tracking moving objects sub-trajectories at each time window, than just last position, it becomes feasible gain insight on behaviour, potentially...

Hot spot policing involves the deployment of police patrols to places where high levels crime have previously concentrated. The creation patrol routes in these hot spots is mainly a manual process that using results from an analysis spatial patterns identify areas and draw officers are required patrol. In this article we introduce computational approach for automating routes. techniques created covered higher than equivalent creating routes, were more efficient how they spots. Although...

Trafi¬c information in big cities can be collected by GPS vehicles or trafi¬c radar, even gathered from tweets. This used to complement generated cameras and physical sensors order guide the actions of public agents short long term. It is also useful support decisions drivers related displacement through city real time near-real time. Through these data it possible analyze where density areas are within discover portions that has more probability have jams. Such discovery may help...

Irrigated agriculture is the most water-consuming sector in Brazil, representing one of main challenges for sustainable use water. This study has investigated and evaluated popular machine learning techniques like Gradient Boosting Random Forest, deep models univariate time series to predict value reference evapotranspiration, a metric water loss from crop environment. The evapotranspiration ET0, plays an essential role irrigation management since it can be used reduce amount that will not...

Crimes (e.g., assault, arson, harassment, and murder) have emerged as one of the most critical problems countries face. In particular, in Brazil, crime is a theme growing interest prime concern some cities, due to high rates, sheer magnitude violence perceived number lives lost. this paper, we aim at predicting crimes each region city before they happen efficiently identify where target police resources that will be used prevent from occurring. A relevant amount approaches available...

It is increasingly common to use chatbots as an interface services. Making this experience more humanized requires the chatbot understand natural language and express itself using language. One crucial step achieve label data with intentions entities. After labeling, one can labeled train a Natural Language Understanding (NLU) component. The NLU component interprets text extracting entities present in that text. Manually onerous impracticable process due high volume of data. Thus,...

The ubiquity of GPS-enabled smartphones and automotive navigation systems allows to monitor collect massive streams trajectory data in real-time. This enables real-time analyses on mobility urban settings, which turn have the potential substantially improve traffic conditions, analyze congested areas, detect events (quasi) real-time, so on. While many existing approaches characterize past movements moving objects from historical data, or address problem finding out clusters streams, such...

Recent approaches for online clustering of moving objects location are restricted to instantaneous positions. Subse-quently, they fail capture the behavior over time. By continuously tracking sub-trajectories object at each time window, it becomes possible gain insight on current and potentially detect mobility patterns in real In our previous work [1], we proposed CUTiS, an incremental algorithm discovering maintaining density-based clusters trajectory data streams, while evolution...

Irrigated agriculture is the most water-consuming sector in Brazil, representing one of main challenges for sustainable use water. This study proposes and experimentally evaluates univariate time series models that predict value reference evapotranspiration, a metric water loss from crop to environment. Reference evapotranspiration plays an essential role irrigation management since it can be used reduce amount will not absorbed by crop. The experiments performed under meteorological dataset...