Andrea de GiorgioArtificial Engineering
Andrea de Giorgio
PhD
Helping Startups and SMEs to succeed with Artificial Intelligence
About
36
Publications
25,805
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
321
Citations
Introduction
Andrea de Giorgio is working on machine learning, knowledge representation, visualization (including mixed reality technologies) and transfer learning in engineering and medical applications. Contacts and further details on https://artificial.engineering
Additional affiliations
September 2021 - February 2022
November 2015 - January 2016
January 2016 - September 2021
Publications
Publications (36)
This paper outlines the main steps towards an open and adaptive simulation method for human-robot collaboration (HRC) in production engineering supported by virtual reality (VR). The work is based on the latest software developments in the gaming industry, in addition to the already commercially available hardware that is robust and reliable. This...
This article argues that an efficient artificial intelligence control algorithm needs the built-in symmetries of an industrial robot manipulator to be further characterized and exploited. The product of this enhancement is a four-dimensional (4D) discrete cylindrical grid space that can directly replace complex robot models. A* is chosen for its wi...
Literature shows that reinforcement learning (RL) and the well-known optimization algorithms derived from it have been applied to assembly sequence planning (ASP); however, the way this is done, as an offline process, ends up generating optimization methods that are not exploiting the full potential of RL. Today's assembly lines need to be adaptive...
The training of future experts and operators in manufacturing engineering relies on understanding procedural processes that require applied practice. Yet, current manufacturing education and training overwhelmingly continues to depend on traditional pedagogical methods that segregate theoretical studies and practical training. While educational ins...
Class imbalance (CI) is a well-known problem in data science. Nowadays, it is affecting the data modeling of many of the real-world processes that are being digitized. The manufacturing industry turns out to be highly affected by this problem, especially in fault inspection, prediction or monitoring processes, and in all those processes where the p...
The Routledge Handbook of Artificial Intelligence and Geopolitics examines how machines, algorithms, and data are reshaping the way nations interact, negotiate, and navigate global politics.
In the 21st Century, Artificial intelligence (AI) has transformed from a theoretical wonder to a real force, and with it the race to dominate new technologies...
Purpose
This bibliometric analysis of the top 100 cited articles on extended reality (XR) in neurosurgery aimed to reveal trends in this research field. Gender differences in authorship and global distribution of the most-cited articles were also addressed.
Methods
A Web of Science electronic database search was conducted. The top 100 most-cited a...
Molti pensano che l'intelligenza artificiale debba essere usata per grandi applicazioni, ma in realtà anche delle applicazioni minori ma con un focus ben preciso possono servire ad ottimizzare processi industriali complessi. In particolare, questa presentazione si riferisce ai processi della produzione alimentare e riporta alcuni dei più comuni cas...
Clinical prediction models for spine surgery applications are on the rise, with an increasing reliance on machine learning (ML) and deep learning (DL). Many of the predicted outcomes are uncommon; therefore, to ensure the models’ effectiveness in clinical practice it is crucial to properly evaluate them. This systematic review aims to identify and...
In the context of Industry 4.0, companies understand the advantages of performing Predictive Maintenance (PdM). However, when moving towards PdM, several considerations must be carefully examined. First, they need to have a sufficient number of production machines and relative fault data to generate maintenance predictions. Second, they need to ado...
Learning factories are realistic manufacturing environments built for education; many universities have recently introduced learning factories in engineering programs to tackle real industrial problems; however, statistical studies on its effectiveness are still scarce. This paper presents a statistical study on the impact of learning factories on...
Surgical simulation practices have witnessed a rapid expansion as an invaluable approach to resident training in recent years. One emerging way of implementing simulation is the adoption of extended reality (XR) technologies, which enable trainees to hone their skills by allowing interaction with virtual 3D objects placed in either real-world image...
The fourth industrial revolution is based on a few technological advancements that promise an industrial transformation based on achieving sharing and circular economies. Selecting and applying these advancements correctly, i.e., following relevant value drivers, is a key to the success of manufacturing firms. This results in an increasing body of...
Despite the recent increase in Virtual Reality (VR) technologies employed for training manufacturing operators on industrial robotic tasks, the impact of VR methods compared to traditional ones is still unclear. This paper presents an experimental comparison of the two training approaches, with novice operators performing the same manufacturing tas...
Since the introduction of the concept of learning curves in manufacturing, many articles have been applying the model to study learning phenomena. In assembly, several studies present a learning curve when an operator is trained over a new assembly task; however, when comparisons are made between learning curves corresponding to different training...
Can automatically authored videos of industrial operators help other operators to learn procedural tasks? This question is relevant to the advent of the industrial internet of things (IIoT) and Industry 4.0, where smart machines can help human operators rather than replacing them in order to benefit from the best of humans and machines. This study...
Industrial processes are mainly based on procedural knowledge that must be continually elicited from experienced operators and learned by novice operators. In the context of Industry 4.0, machines already play a key role in knowledge transfer; however, new models and methods based on the artificial intelligence advances of the past few years need t...
This article is a citation review of the publication "A hybridization of genetic algorithms and fuzzy logic for the single-machine scheduling with flexible maintenance problem under human resource constraints" published in 2017 by Touat et al. in Applied Soft Computing. A citation review is a widely neglected scientific method, refined by de Giorgi...
The procedural knowledge block (PKB) is a model developed by Andrea de Giorgio to formulate procedural knowledge. This dataset corresponds to PKB descriptions of locomotive assembly videos collected in 2020.
This article argues that despite a citation review is a rarely used research tool, this can be very useful to assess the impact of new research topics, both from the future research direction and the bibliometric perspectives. An explorative study is presented around the research area marked as Industry 4.0 with the conference paper mentioned in th...
This is the version of the Matlab & RAPID code released with the scientific article A. de Giorgio and L. Wang, "Artificial Intelligence Control in 4D Cylindrical Space for Industrial Robotic Applications", in IEEE Access, vol. 8, pp. 174833-174844, 2020, doi: 10.1109/ACCESS.2020.3026193.
Questo articolo scientifico sostiene la tesi che un algoritmo di controllo, facente uso di intelligenza artificiale, per poter essere efficiente necessiti di sfruttare le simmetrie integrate in ogni manipolatore robotico industrale così che quest’ultimo possa essere ulteriormente caratterizzato ed utilizzato. Il prodotto di questo miglioramento è u...
In the age of digital manufacturing there is a need to elicit and transfer procedural knowledge between humans and machines. Having proper knowledge is essential in decision-making. The more the knowledge, the better decisions are made. To capture experiences and turn them into knowledge is fundamental in learning processes and knowledge developmen...
It's almost 2 years that I have been trying to answer the question below, and now the first scientific article of a series is published with my answer: "Procedural knowledge and function blocks for smart process planning": https://doi.org/10.1016/j.promfg.2020.05.148 (open access)
This book is the fruit of an Italian-Swedish collaborative project involving the Rotary Stockholm International (District 2350), the University of Florence and The Rotary Club
Firenze Sud (District 2071).
The book opens with a section on Alfred Nobel and his ties to Italy, the city of Sanremo in particular. Most of the book is dedicated to two winn...
We have tried to generate feasible assembly sequences with Monte Carlo Tree Search (MCTS), a reinforcement learning algorithm. Results are not good, but they suggest that the problem might be about having a good heuristic to identify good sub-assemblies during the tree search.
We have tried to generate feasible assembly sequences with Q-learning, a reinforcement learning algorithm. Results are encouraging.
The presentation is a literature review on current issues related to Deep Reinforcement Learning code, benchmarking and reproducibility. We do not own the numerical or graphical results and they are randomly taken from literature for the sole purpose of displaying concrete examples of the problems described. Our work consisted of putting together t...
Presentation of conference paper at FAIM 2017: Human-machine collaboration in virtual reality for adaptive production engineering
Variable selection techniques are employed in statistical modelling process in order to reduce the number of predictor variables that are part of the model of the experiment under study.
Fractional factorial experiments are experimental designs consisting of chosen subsets (fractions) of the test runs of full factorial experimental designs. A subset is chosen so as to reduce the number of test runs, while maximizing the experimental results on the main factors of the problem studied. The content of the presentation is an excerpt fr...
Distributed and hierarchical models of control are nowadays popular in computational modeling and robotics. In the artificial neural network literature, complex behaviors can be produced by composing elementary building blocks or motor primitives, possibly organized in a layered structure. However, it is still unknown how the brain learns and encod...
Restricted Boltzmann Machines (RBMs) and autoencoders have been used - in several variants - for similar tasks, such as reducing dimensionality or extracting features from signals. Even though their structures are quite similar, they rely on different training theories. Lately, they have been largely used as building blocks in deep learning archite...
In this thesis I demonstrated how a singular neural network can potentially represent the set of more latent neural circuits, able to execute different functions, based on an input encoding so to reprogram their functionality. Such programmable structure, in passing from one behavior to another, does not require further learning procedures, nor any...
Questions
Questions (15)
Q* (pronounced Q-Star) was mentioned by the news agency Reuters as a breakthrough at OpenAI. What is it about? Are there any scientific articles that may illuminate us or is it an "industrial secret"?
I have two learning curves that need to be compared to establish which learning method is better. Each learning curve is estimated with 11 samples for each of 5 repetitions (total 55 samples per learning curve). Is there a better method than comparing 11 samples on learning curve A with 11 samples on learning curve B at each repetition (five comparisons) with ANOVA?
Thanks in advance for your answers or comments, I will recommend everyone who answers something useful.
A few scientific journals have started implementing a "publish, then review" model of publishing. It is explained well in this article:
Are there any reasons why this model should not become the main one in the future?
Elsevier announced that Mendeley profiles will be discontinued from December.
There is a study ( ) that confirms the value of Mendeley reader counts as an early scientific impact indicator. In fact, the correlation between reader counts and citations stabilizes in about 5 years.
What will be of the reader counts in Mendeley without the profiles to show them? Do other platforms have similar parameters that one can read beside RG?
Note that RG read counts don't necessarily mean that users have saved the read research into their own reference databases for a future citation (as Mendeley reader counts show).
