An innovative virtual sensing system for the vehicle-centric evaluation of emissions in the sustainable mobility transition.

The objective of the research is to develop a new methodology capable of quantifying the emissions of internal combustion engine cars based not only on their technology but also on the dynamic behavior of the individual vehicle. No complicated exhaust measurement apparatus is needed. Employing just a telematic device equipped with GNSS and an inertial measurement unit, which can be easily attached to the vehicle, we demonstrate how individualised, accurate climate-altering emissions result by using figures extracted from European test databases, appropriately combined with real travelled distances, speeds, and driving style of each individual car. Pollutant emissions are, in this paper, also assessed though in a more general manner, and this represents a starting point for a future complete vehicle-centric emissions evaluation. This research demonstrates that circulating car emissions have to be assessed considering not only the Euro class and type of fuel, but also how the vehicle is driven. In this work a new, implementation oriented methodology is proposed in order to properly merge average European standard emission data with car-based telematic measures to highlight a new paradigm for regulating in a more conscious way the transition of the internal combustion engine car park towards a large scale, sustainable mobility ecosystem. This approach would place greater responsibility on the driver, without leaving anyone behind and without compelling the car scrapping solely based on the Euro class of its engine. The key contribution is ultimately to establish an easy to handle methodology enabling targeted and behavior-based traffic management policies. In fact, through a massive telematics recent dataset, the proposed virtual emission sensing system reveals that an extensive and inefficient use of eco-friendly vehicles produces much more greenhouse gas emissions than older vehicles driven in an environmentally responsible way.

MIRACLE: MInd ReAding CLassification Engine.

Brain-computer interfaces (BCIs) have revolutionized the way humans interact with machines, particularly for patients with severe motor impairments. EEG-based BCIs have limited functionality due to the restricted pool of stimuli that they can distinguish, while those elaborating event-related potentials up to now employ paradigms that require the patient's perception of the eliciting stimulus. In this work, we propose MIRACLE: a novel BCI system that combines functional data analysis and machine-learning techniques to decode patients' minds from the elicited potentials. MIRACLE relies on a hierarchical ensemble classifier recognizing 10 different semantic categories of imagined stimuli. We validated MIRACLE on an extensive dataset collected from 20 volunteers, with both imagined and perceived stimuli, to compare the system performance on the two. Furthermore, we quantify the importance of each EEG channel in the decision-making process of the classifier, which can help reduce the number of electrodes required for data acquisition, enhancing patients' comfort.