Ricerc@Sapienza

Civil infrastructures, such as tunnels and bridges, are directly related to the overall economic and demographic growth of countries.
The aging of these infrastructures increases the probability of catastrophic failures that results in loss of lives and high repair costs;
all over the world, these factors drive the need for advanced infrastructure monitoring systems. For these reasons, in the last years,
different types of devices and innovative infrastructure monitoring techniques have been investigated to automate the process and

Automated pavement crack detection and measurement are important road issues. Agencies have to guarantee the improvement of road safety. Conventional crack detection and measurement algorithms can be extremely time-consuming and low efficiency. Therefore, recently, innovative algorithms have received increased attention from researchers. In this paper, we propose an ensemble of convolutional neural networks (without a pooling layer) based on probability fusion for automated pavement crack detection and measurement.

Automatic crack detection from images is an important task that is adopted to ensure road safety and durability for Portland cement concrete (PCC) and asphalt concrete (AC) pavement. Pavement failure depends on a number of causes including water intrusion, stress from heavy loads, and all the climate effects. Generally, cracks are the first distress that arises on road surfaces and proper monitoring and maintenance to prevent cracks from spreading or forming is important. Conventional algorithms to identify cracks on road pavements are extremely time-consuming and high cost.

In developing countries, crop field productivity is particularly vulnerable to spreading diseases, including viruses and fungi. This is mostly due to the lack of skilled plant pathologists as well as to the scarce fund and poor infrastructure (e.g., roads, power and water lines) availability.
The PlantVillage project through its mobile application named Nuru provides an AI digital assistant to recognize plants and their diseases through image analysis.

The management of plastic debris is a serious issue due to its durability. Unfortunately, million
tons of plastic end up in the sea becoming one of the biggest current environmental problems. One way to
monitor the amount of plastic in beaches is to collect samples and visually count and sort the plastic particles
present in them. This is a very time-consuming task. In this work, we present a Computer Vision-based
system which is able to automatically count and classify microplastic particles (1-5 mm) into five different

Let us consider questions like: What is the current state of output? What will be the evolution of prices in the short future? Are they increasing or decreasing? Is it thundering right now and what is the situation off the sea? These questions which at a first glance seem unrelated have one thing in common; they all challenge researchers to make very quick decisions about the conditions around them, to nowcast, as it is commonly called. Every airport needs a nowcasting mechanism for the weather; likewise, every Central Bank should have a nowcasting system for economic aggregates.

A novel deep learning approach is proposed for the predictive analysis of trends in energy related time series, in particular those relevant to photovoltaic systems. Aim of the proposed approach is to grasp the trend of the time series, namely, if the series goes up, down or keep stable, instead of predicting the future numerical value. The modeling system is based on Long Short-Term Memory networks, which are a type of recurrent neural network able to extract information in samples located very far from the current one.

A novel deep learning approach in proposed in this paper for multivariate prediction of energy time series. It is developed by using Convolutional Neural Network and Long Short-Term Memory models, in such a way that several correlated time series can be joined and filtered together considering the long term dependencies on the whole information. The learning scheme can be viewed as a stacked deep neural network where one or more layers are superposed, feeding their output in the sequent layer's input.

In smart grids and microgrids, time series prediction is a fundamental tool for enabling intelligent energy resource management and advanced interactions between heterogeneous agents. In this work, we propose a solution to the energy forecasting problem based on two machine learning techniques: Convolutional Neural Network and Long Short-Term Memory Network. These techniques are combined with a new embedding format to appropriately feed the time series to the stacked network architecture.

We propose a deep learning approach for multivariate forecasting of energy time series. It is developed by using Long Short-Term Memory deep neural networks so that different related time series, incorporating information of longterm dependencies, can be joined together as a multidimensional input of the deep neural network. The learning scheme can be represented as a stacked LSTM network in which one or more layers are cascaded, feeding their output to the input of the sequent layer.