Is bigger always better? A controversial journey to the center of machine learning design, with uses and misuses of big data for predicting water meter failures

Abstract

If modern artificial intelligence (AI) comes often misunderstood, this is mainly due to the fact that, historically, it is solely tied to the way human brains work and think. New machine learning (ML) algorithms, instead, learn now by processing massive piles of data. This process enables machines to adapt to real-world situations, as well as to propose suggestions on how to classify and interpret a variety of different real phenomena. Simply speaking, the deployment of modern ML systems into critical applications is directly influenced by the way training data are organized and modeled [1-3]. Hence, while those modern algorithms rapidly sift through huge datasets, loaded with millions of information, a thoughtfully designed AI, beyond its ML-based core, should never disregard the fact that algorithms that learn are, for now, just another form of machine instruction, still guided and influenced by the potential and the limitations that training data carry with them. In other words, even when we train algorithms to learn basic associations that can then be used to approximate,

A Cross-Regional Analysis of the COVID-19 Spread during the 2020 Italian Vacation Period: Results from Three Computational Models Are Compared

“…We have had other previous experience with this kind of model, both to investigate how the COVID-19 spreads and we have also utilized it in other fields [ 29 , 30 , 31 , 32 , 33 ]. Here, the first fact to note is that we input to our ANN the same dataset, comprised of white and black windows (with relative numbers of infections and tourists), that was used with the GLM.…”

On the probabilistic mind of a robot

“…With reference to the above discussion, and to give a pragmatic example of the importance of the role that the decision threshold can play, we briefly touch upon a case we recently studied (Roccetti et al, 2019). We worked with an Italian company to spot malfunctioning mechanical water meters which are used to measure how much water is consumed over a given period of time.…”

“…And even if DNN technologies are often described as black boxes; in the context of a DNN-based artificial mind, those probabilistic factors that have led to a given decision can be quantified to a very precise extent. In other words, what we are trying to say is that the decisions taken by an artificial mind always have valid motivations, so long as we are given the probabilistic values that that artificial mind has computed for the different alternatives in play (Roccetti et al, 2019;Villani et al, 2018). Simply told, the meaning of likely, for artificial minds, like those we have discussed so far, is never vague or fuzzy, but it obeys well-known probability theories.…”

An alternative approach to dimension reduction for pareto distributed data: a case study

“…Along this line, in this paper we describe a deep learning design experience, where we had initially a trouble on developing an appropriate deep learning model able to detect failures in mechanical water meter devices, because we tried to train that model by merging together the numerical information relative to water consumption with some device descriptors based on categorical information, thus resulting into an explosion in data dimensionality, that soon determined a deterioration of the prediction accuracy [ 8 , 9 ]. After several unsuccessful experiments conducted with alternative methodologies that either permitted to reduce the data space dimensionality or employed more traditional machine learning algorithms, we changed the training strategy.…”