Rafael Canal

Data extracted directly from a vehicle’s electronic control unit (ECU) play a crucial role in the automotive industry because they contain valuable information from the engine and electronic parts. These data have the potential to enable compliance analysis, detect faults and errors, and guarantee driver and car safety as well as product quality. Among the possible uses of the data from the ECUs, driving profile analysis and fuel consumption prediction stand out, which enable analyses for insurers and transportation companies, and help to reduce fuel consumption and greenhouse gases, in addition to providing feedback to the driver. In this work, we apply machine learning algorithms to real data from an engine ECU to examine the driver’s driving behavior and accurately classify their fuel efficiency. Moreover, we develop regression models that predict fuel consumption for vehicles in operation. To ensure the effectiveness of our models, we carefully select variables strongly correlated with fuel consumption using a feature selection process. Compared to related works, both our profile classification results in precision, recall, and accuracy metrics, and our regression models result in the metrics of mean square errors, mean absolute error, and coefficient of determination, which are superior or similar. Notably, our algorithms exhibit lower computational costs and enable real-time analysis by utilizing a cloud server.

The vehicle testing–validation phase is a crucial and demanding task in the automotive development process for vehicle manufacturers. It ensures the correct operation, safety, and efficiency of the vehicle. To meet this demand, some commercial solutions are available on the market, but they are usually expensive, have few connectivity options, and are PC-dependent. This paper presents an IoT-based intelligent low-cost system for vehicle data acquisition during on-road tests as an alternative solution. The system integrates low-cost acquisition hardware with an IoT server, collecting and transmitting data in near real-time, while artificial intelligence (AI) algorithms process the information and report errors and/or failures to the manufacturing engineers. The proposed solution was compared with other commercial systems in terms of features, performance, and cost. The results indicate that the proposed system delivers similar performance in terms of the data acquisition rate, but at a lower cost (up to 13 times cheaper) and with more advanced features, such as near real-time intelligent data processing and reduced time to find and correct errors or failures in the vehicle.

Mazk is an intelligent tutor that aims to assist the student, with the support of the computer and using techniques of Artificial Intelligence, in the teaching-learning process. Currently, all content made available to Mazk is updated manually by the human tutor. Considering the increasing amount of educational materials available, this process often becomes tiring and time-consuming. In order to optimize this task, this paper demonstrates a proposal of automatic generation of content for Mazk.