Ricerc@Sapienza

Complex-valued neural networks (CVNNs) are a powerful modeling tool for domains where data can be naturally interpreted in terms of complex numbers. However, several analytical properties of the complex domain (such as holomorphicity) make the design of CVNNs a more challenging task than their real counterpart. In this paper, we consider the problem of flexible activation functions (AFs) in the complex domain, i.e., AFs endowed with sufficient degrees of freedom to adapt their shape given the training data.

Smart grids, microgrids, and pure electric powertrains are the key technologies for achieving the expected goals concerning the restraint of CO₂ emissions and global warming. In this context, an effective use of electrochemical energy storage systems (ESSs) is mandatory. In particular, accurate state of charge (SoC) estimations are helpful for improving the ESS performances. To this aim, developing accurate models of electrochemical cells is necessary for implementing effective SoC estimators. Therefore, a novel neural network modeling technique is proposed in this paper.

Algal blooms of the water are an important variable for the analysis of freshwater ecosystems, which are relevant not only for human populations but also for plant and animal diversity. Monitoring algal blooms from space allows for a continuous and automatic control without the necessity of water sampling and human intervention. However, it is a very challenging task, which becomes particularly difficult when dealing with cyanobacteria blooms.

The study on the functioning of HVAC systems and hydraulic circuits in buildings has highlighted the energy limits of a static management of the parameters that regulate them. The main recurring problems regard inadequate maintenance, failures, losses and malfunctions. With the development of new digital methodologies on the management of data flows (BIM and IoT) it has been demonstrated how the dynamic analysis of the sys-tems functioning parameters can lead to wide margins of improvement in terms of ener-gy use and containment of energy costs.