- 2020 - 202236125
- 2010 - 201913629
- 2000 - 20091236
- 1990 - 19998
- 1980 - 19896
- 1970 - 19792
- 1957 - 19591
- Settore SECS-S/01 - Statistica1497
- Settore ING-INF/05 - Sistemi di E...822
- Settore SECS-P/07 - Economia Azie...693
- Settore ING-INF/06 - Bioingegneri...553
- Settore ING-INF/01 - Elettronica506
- Settore FIS/05 - Astronomia e Ast...459
- Settore ING-INF/04 - Automatica414
- Settore FIS/02 - Fisica Teorica, ...391
Accesso al fulltext
- no fulltext8874
- partially open2
Biostimolanti, strumento sinergico nella concimazione delle specie orticole: applicazioni su lattuga
Studio su uno strumento di integrazione nella fertilizzazione in orticoltura, per l'aumento della sostenibilità di questa. Nell'elaborato si affrontano i problemi, soprattutto ambientali, legati alle fertilizzazione inorganica in forte crescita dalla rivoluzione verde in poi. Nell'affrontare le problematiche delle fertilizzazioni in una via più sostenibile si propone come strumento, i biostimolanti. Si affronta l'argomento, dando definizione e classificazione di questi e riportando diversi ca...
The NV center in diamond, due to its versatility, has emerged as a leading contender for nodes in quantum networks, offering the advantage of optical control even at room temperature. However, the challenge lies in the spectral jumps in the emission frequencies, which, over time, cause the optical lasers to lose resonance. For a reliable quantum Internet, swift and efficient tuning is crucial. In this work, we developed a physical model based on the stochastic master equation, which effective...
Water systems around the world are under increasing pressure year by year. Large numbers of the world's population currently live in water-stressed areas, and with current trends that will only get worse. Using smart city technology is a way to optimise current systems, using water meters to continuously record information about consumption levels and measurement instruments within the pipes to convey data. In this thesis we will treat the problem of cleansing the data coming directly from th...
Machine learning approach for structural timber strength grading starting from the computed tomography of the log
All timber used for structural purpose in the European Union has to be strength graded. To grade a board to possibilities exist: visual grading and machine grading. While both methods serve the purpose, mechanical grading stands out for its superior reliability. Machine strength grading entails subjecting each timber piece to specialized machines that determine the indicative properties required to assign an appropriate grade. This work, carried out at Microtec, proposes to use a machine lear...
Deep Learning in Banking Risk Management: A Comparative Assessment of LSTM Network and Nelson-Siegel Stochastic Modeling
This thesis presents a comprehensive quantitative analysis of traditional yield curve models and advanced deep learning architectures, with a special focus on the Nelson-Siegel-Svensson model and Long Short-Term Memory networks. The objective is to rigorously evaluate and benchmark these models with both in-sample and out-of-sample forecasts, placing a strong emphasis on their applicability in simulating different interest rate evolution scenarios. This research is propelled by the primary ai...
The aim of this master's thesis project is to demonstrate the feasibility of an online selection process for the phase 2 scouting system at CMS. The focus is on a rare decay of W to 3 pi particles, which forms the basis of the selection process. The initial phase involves a concise analysis with the objective of establishing an upper limit on the branching fraction for the decay of the W boson. To achieve this, Monte Carlo simulations of the Phase 2 scouting data are utilized, providing valua...
Development of a framework to evaluate and characterise Deep Learning models used for deep-fake detection in the identity fraud industry.
The identity fraud industry has been developing computer vision models based on Deep Learning techniques to identify deep-fake images of people's faces that could be used, for example, to open bank accounts. The work aims to identify image properties that are relevant to characterize the performance of the binary classifier, this information would provide valuable insights for the design and training of the models. In this work, we are following two research lines: inquiring about intrinsic i...
The outbreak of an infectious disease transmitted with close contacts does not only depend on the characteristic of the infection, but also on human-to-human contact behavior. This aspect is difficult to capture in physics model of epidemics because human behavior presents complex patterns: heterogeneities, recurrence, and spatial and temporal correlations. Key statistical features of human contact patterns are being uncovered by the increasing efforts to collect contact data in selected coho...
Artificial Intelligence and deep learning are playing key roles in the filed of anomaly detection and predictive maintenance. The goal of this work is to incorporate Machine Learning and Auto ML techniques in the context of Safe Storages, which can be used for different purposes like storing valuable items in banks. The first phase of this program is to build machine learning models or incorporate language models like Chatgpt and other Auto ML techniques in order to construct a virtual engine...
A partire dagli anni ’90, estesi fenomeni di deperimento e moria hanno interessato con sempre maggiore frequenza tutte le specie del genere Fraxinus diffuse in Europa. La malattia osservata per la prima volta su frassino maggiore (Fraxinus excelsior) in Polonia, si diffuse rapidamente in oltre 20 stati del vecchio continente causando gravi danni dal punto di vista sia ecologico che economico. In Italia, i primi sintomi furono osservati in Friuli Venezia Giulia nel 2009, e successivamente nell...