O projeto “Aquaponia” consiste em um sistema aquapônico, com funcionamento controlado por um Raspberry Pi. Através de sensores Aquaponia realiza a coleta de dados, como temperatura, umidade do ar, iluminação, etc. Atuadores programados podem controlar a iluminação, o funcionamento de bombas e até o controle do ar condicionado da sala.
Um algoritmo está sendo desenvolvido, com bases nos dados obtidos dos sensores, para inferir a situação do aquário e da horta e sugerir que ações sejam tomadas. Por exemplo, o sistema poderia antecipar uma eventual queda de temperatura, e regular o ar condicionado de forma a otimizar o crescimento das plantas, sem prejudicar o bem-estar dos peixes.
Essa linha de pesquisa está se destacando atualmente na academia devido à importância de sensores, com pouca capacidade de processamento, em smart-farms, carros autônomos, segurança e automatização residencial, etc.
Única equipe de graduação da américa latina a desenvolver Veículos Submarinos Autônomos (AUV's) e o nosso objetivo é participar da maior competição de automação naval do mundo, a RoboSub, para representar o Brasil. Durante um ano, nos esforçamos ao máximo para desenvolver um projeto que mostre excelência e inovação puramente nacionais.
Internet of things (IoT) is envisioned as the interconnection of the Internet with sensing and actuating devices. IoT systems are usually designed to collect massive amounts of data from multiple and possibly conflicting sources. Nevertheless, data must be refined before being stored in a repository, so as information can be correctly extracted for further uses. Knowledge fusion is an important technique to identify and eliminate erroneous data from compromised sources or any mistakes that might have occurred during the extraction process. We propose a new multisensor data fusion algorithm for IoT that supports the knowledge extraction needed to adapt knowledge graphs. This algorithm, named Athena, enhances accuracy when compared to the traditional multisensor data fusion techniques. We also discuss the role of reinforcement learn over integration on a multi-application WSAN.
In order to achieve optimum yields in oil palm, management practices should be tailored to the crop site agro-ecological conditions. Nevertheless, oil palm farmers often have to make decisions based on a limited knowledge base. Considering that water management is a critical aspect of oil palm crops, this paper describes an inference method for irrigation decision-making in oil palm supported on soil moisture and vapor pressure deficit data. Under an ideal scenario where this agrometeorological data is available through a Wireless Sensor Network (WSN) at a crop plot resolution, we formulated a method to prevent oil palm farmers to submit their crops to water deficit stress. The inference method was based on a Data Fusion technique called Dempster-Shafer Inference, which is convenient for the use of uncertain data with distinct levels of detail such as those present in a WSN. The outcome of fusing soil moisture …
While wireless sensor networks (WSNs) have been traditionally tasked with single applications, in recent years we have witnessed the emergence of WSNs that allow the sensing and communication infrastructure to be shared among multiple applications thus optimizing the use of resources. As the number of applications in a WSN increases, a growing amount of sensor-generated data will be produced, from which useful information can be extracted. A major requirement in these networks is to save energy in order to extend their operational lifetime. However, wireless sensors and actuators commonly rely on batteries as their energy sources, whose replacement is undesirable or unfeasible. Among the methods employed to extend network lifetime, Multisensor data fusion (MDF) is one of the most widely used. Traditional MDFs are not able to identify different contexts, since they are designed using an application …
