The paper illustrates a part of the research activity conducted by authors in the field of electric Short Term Load Forecasting (STLF) based on Artificial Neural Network (ANN) architectures. Previous experiences with basic ANN architectures have shown that, even though these architectures provide results comparable with those obtained by human operators for most normal days, they evidence some accuracy deficiencies when applied to ''anomalous'' load conditions occurring during holidays and long weekends. For these periods a specific procedure based upon a combined (unsupervised/supervised) approach has been proposed. The unsupervised stage provides a preventive classification of the historical load data by means of a Kohonen's Self Organizing Map (SOM) The supervised stage, performing the proper forecasting activity, is obtained by using a multi-layer perceptron with a backpropagation learning algorithm similar to the ones above mentioned. The unconventional use of information deriving from the classification stage permits the proposed procedure to obtain a relevant enhancement of the forecast accuracy for anomalous load situations

In this paper, we propose a new sensor for the detection and analysis of dusts (seen as powders and fibers) in indoor environments, especially designed for applications in the field of Cultural Heritage or in other contexts where the presence of dust requires special care (surgery, clean rooms, etc.). The presented system relies on image processing techniques (enhancement, noise reduction, segmentation, metrics analysis) and it allows obtaining both qualitative and quantitative information on the accumulation of dust. This information aims to identify the geometric and topological features of the elements of the deposit. The curators can use this information in order to design suitable prevention and maintenance actions for objects and environments. The sensor consists of simple and relatively cheap tools, based on a high-resolution image acquisition system, a preprocessing software to improve the captured image and an analysis algorithm for the feature extraction and the classification of the elements of the dust deposit. We carried out some tests in order to validate the system operation. These tests were performed within the Sistine Chapel in the Vatican Museums, showing the good performance of the proposed sensor in terms of execution time and classification accuracy.

This article describes a new instrument for power quality (PQ) measurements based on the Raspberry-Pi. This is the latest step of a long study started by the Electric and Electronic Measurements Laboratory of "Roma Tre" University 12 years ago. During this time, the Laboratory developed and refined instrumentation for high accuracy power quality measurements. Through its own architecture, the new instrument allows the use of the Raspberry instead of a personal computer (PC). The data acquired and locally processed are then sent to a remote server where they can be shown to users. Imagines of the system and of the data prove the activity of the system.

No abstract

No abstract