RESUMO
The advent of 5G will bring a massive adoption of IoT devices across our society. IoT Applications (IoT Apps) will be the primary data collection base. This scenario leads to unprecedented scalability and security challenges, with one of the first areas for these applications being Smart Cities (SC). IoT devices in new network paradigms, such as Edge Computing and Fog Computing, will collect data from urban environments, providing real-time management information. One of these challenges is ensuring that the data sent from Edge Computing are reliable. Blockchain has been a technology that has gained the spotlight in recent years, due to its robust security in fintech and cryptocurrencies. Its strong encryption and distributed and decentralized network make it potential for this challenge. Using Blockchain with IoT makes it possible for SC applications to have security information distributed, which makes it possible to shield against Distributed Denial of Service (DDOS). IoT devices in an SC can have a long life, which increases the chance of having security holes caused by outdated firmware. Adding a layer of identification and verification of attributes and signature of messages coming from IoT devices by Smart Contracts can bring confidence in the content. SC Apps that extract data from legacy and outdated appliances, installed in inaccessible, unknown, and often untrusted urban environments can benefit from this work. Our work's main contribution is the development of API Gateways to be used in IoT devices and network gateway to sign, identify, and authorize messages. For this, keys and essential characteristics of the devices previously registered in Blockchain are used. We will discuss the importance of this implementation while considering the SC and present a testbed that is composed of Blockchain Ethereum and real IoT devices. We analyze the transfer time, memory, and CPU impacts during the sending and processing of these messages. The messages are signed, identified, and validated by our API Gateways and only then collected for an IoT data management application.
RESUMO
There is a constant risk of iron ore collapsing during its transfer between processing stages in beneficiation plants. Existing instrumentation is not only expensive but also complex and challenging to maintain. In this research, we propose using edge artificial intelligence for early detection of landslide risk based on images of iron ore transported on conveyor belts. During this work, we defined the device edge and the deep neural network model. Then, we built a prototype will to collect images that will be used for training the model. This model will be compressed for use in the device edge. This same prototype will be used for field tests of the model under operational conditions. In building the prototype, a real-time clock was used to ensure the synchronization of image records with the plant's process information, ensuring the correct classification of images by the process specialist. The results obtained in the field tests of the prototype with an accuracy of 91% and a recall of 96% indicate the feasibility of using deep learning at the edge to detect the type of iron ore and prevent its risk of avalanche.