Neural Networks for Hyperspectral Imaging of Historical Paintings: A Practical Review.

Hyperspectral imaging (HSI) has become widely used in cultural heritage (CH). This very efficient method for artwork analysis is connected with the generation of large amounts of spectral data. The effective processing of such heavy spectral datasets remains an active research area. Along with the firmly established statistical and multivariate analysis methods, neural networks (NNs) represent a promising alternative in the field of CH. Over the last five years, the application of NNs for pigment identification and classification based on HSI datasets has drastically expanded due to the flexibility of the types of data they can process, and their superior ability to extract structures contained in the raw spectral data. This review provides an exhaustive analysis of the literature related to NNs applied for HSI data in the CH field. We outline the existing data processing workflows and propose a comprehensive comparison of the applications and limitations of the various input dataset preparation methods and NN architectures. By leveraging NN strategies in CH, the paper contributes to a wider and more systematic application of this novel data analysis method.

Edge-Based Transfer Learning for Classroom Occupancy Detection in a Smart Campus Context.

Studies and systems that are aimed at the identification of the presence of people within an indoor environment and the monitoring of their activities and flows have been receiving more attention in recent years, specifically since the beginning of the COVID-19 pandemic. This paper proposes an approach for people counting that is based on the use of cameras and Raspberry Pi platforms, together with an edge-based transfer learning framework that is enriched with specific image processing strategies, with the aim of this approach being adopted in different indoor environments without the need for tailored training phases. The system was deployed on a university campus, which was chosen as the case study. The proposed system was able to work in classrooms with different characteristics. This paper reports a proposed architecture that could make the system scalable and privacy compliant and the evaluation tests that were conducted in different types of classrooms, which demonstrate the feasibility of this approach. Overall, the system was able to count the number of people in classrooms with a maximum mean absolute error of 1.23.

On Supporting University Communities in Indoor Wayfinding: An Inclusive Design Approach.

Mobility can be defined as the ability of people to move, live and interact with the space. In this context, indoor mobility, in terms of indoor localization and wayfinding, is a relevant topic due to the challenges it presents, in comparison with outdoor mobility, where GPS is hardly exploited. Knowing how to move in an indoor environment can be crucial for people with disabilities, and in particular for blind users, but it can provide several advantages also to any person who is moving in an unfamiliar place. Following this line of thought, we employed an inclusive by design approach to implement and deploy a system that comprises an Internet of Things infrastructure and an accessible mobile application to provide wayfinding functions, targeting the University community. As a real word case study, we considered the University of Bologna, designing a system able to be deployed in buildings with different configurations and settings, considering also historical buildings. The final system has been evaluated in three different scenarios, considering three different target audiences (18 users in total): i. students with disabilities (i.e., visual and mobility impairments); ii. campus students; and iii. visitors and tourists. Results reveal that all the participants enjoyed the provided functions and the indoor localization strategy was fine enough to provide a good wayfinding experience.

The Prediction of Body Mass Index from Negative Affectivity through Machine Learning: A Confirmatory Study.

This study investigates on the relationship between affect-related psychological variables and Body Mass Index (BMI). We have utilized a novel method based on machine learning (ML) algorithms that forecast unobserved BMI values based on psychological variables, like depression, as predictors. We have employed various machine learning algorithms, including gradient boosting and random forest, with psychological variables relative to 221 subjects to predict both the BMI values and the BMI status (normal, overweight, and obese) of those subjects. We have found that the psychological variables in use allow one to predict both the BMI values (with a mean absolute error of 5.27-5.50) and the BMI status with an accuracy of over 80% (metric: F1-score). Further, our study has also confirmed the particular efficacy of psychological variables of negative type, such as depression for example, compared to positive ones, to achieve excellent predictive BMI values.

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

Deep learning models are tools for data analysis suitable for approximating (non-linear) relationships among variables for the best prediction of an outcome. While these models can be used to answer many important questions, their utility is still harshly criticized, being extremely challenging to identify which data descriptors are the most adequate to represent a given specific phenomenon of interest. With a recent experience in the development of a deep learning model designed to detect failures in mechanical water meter devices, we have learnt that a sensible deterioration of the prediction accuracy can occur if one tries to train a deep learning model by adding specific device descriptors, based on categorical data. This can happen because of an excessive increase in the dimensions of the data, with a correspondent loss of statistical significance. After several unsuccessful experiments conducted with alternative methodologies that either permit to reduce the data space dimensionality or employ more traditional machine learning algorithms, we changed the training strategy, reconsidering that categorical data, in the light of a Pareto analysis. In essence, we used those categorical descriptors, not as an input on which to train our deep learning model, but as a tool to give a new shape to the dataset, based on the Pareto rule. With this data adjustment, we trained a more performative deep learning model able to detect defective water meter devices with a prediction accuracy in the range 87-90%, even in the presence of categorical descriptors.